Skip to main content

🆕+📊+🤔 Pulse of the library 2025

About

This document presents a Critical Discourse Analysis focused on AI literacy, specifically targeting the role of metaphor and anthropomorphism in shaping public and professional understanding of generative AI. The analysis is guided by a prompt that draws from cognitive linguistics (metaphor structure-mapping), the philosophy of social science (Robert Brown's typology of explanation), and accountability analysis.

All findings and summaries below were generated from detailed system instructions provided to a large language model and should be read critically as interpretive outputs—not guarantees of factual accuracy or authorial intent.

Task 1: Metaphor and Anthropomorphism Audit​

About this task

For each of the major metaphorical patterns identified, this audit examines the specific language used, the frame through which the AI is being conceptualized, what human qualities are being projected onto the system, whether the metaphor is explicitly acknowledged or presented as direct description, and—most critically—what implications this framing has for trust, understanding, and policy perception.

V3 Enhancement: Each metaphor now includes an accountability analysis.

1. The Organismal Metaphor​

Quote: "Pulse of the Library 2025"

  • Frame: Institution as living biological entity
  • Projection: This titular metaphor maps biological vitality and autonomic function onto the institutional structure of libraries. By suggesting the library has a 'pulse,' the text implies it is a living, feeling organism capable of health or sickness, rather than a constructed organization of policies, infrastructure, and labor. While common in business discourse, in the context of AI, this framing prepares the reader to view technological integration as a 'medical' or 'evolutionary' necessity for survival—keeping the heart beating—rather than a procurement choice. It obscures the mechanical and administrative nature of the institution, suggesting that without the 'infusion' of new technology (like Clarivate's AI), the organism might perish.
  • Acknowledgment: Direct (Unacknowledged) (The metaphor appears in the title and throughout the report as a factual descriptor of the report's function without qualification or scare quotes.)
  • Implications: Framing the library as a living body with a 'pulse' naturalizes the intervention of vendors as 'doctors' or 'life support.' It creates an emotional urgency—monitoring a pulse is a critical care activity. In the context of AI adoption, this suggests that integrating AI is a matter of biological survival ('evolve or die') rather than a strategic, optional decision. It diverts attention from the political economy of library funding and staffing (the actual lifeblood) toward a vague sense of vitality that can be measured and treated by external consultants and technology providers.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The metaphor of a 'pulse' abstracts the library into a single entity, erasing the thousands of individual librarians, administrators, and funders who actually comprise the field. It suggests the 'state of the library' is a natural phenomenon to be observed, rather than a result of specific funding decisions (often cuts) and corporate pricing models. Clarivate, the author, is positioned as the objective observer taking the pulse, obscuring their role as a vendor actively shaping the conditions they are measuring.
Show more...

2. AI as Autonomous Force​

Quote: "Artificial intelligence is pushing the boundaries of research and learning."

  • Frame: AI as physical agent/pioneer
  • Projection: This metaphor projects physical agency and intentionality onto the computational process. 'Pushing boundaries' implies that AI is an active explorer or pioneer with the desire and strength to expand frontiers. It attributes the distinct human capacity for challenging the status quo (a conscious, wilful act) to software. This obscures the reality that algorithms simply process data within the mathematical boundaries defined by their architecture and training sets. The AI does not 'push'; it calculates vectors based on existing data distributions. The agency of the researchers using the tools is transferred to the tools themselves.
  • Acknowledgment: Direct (Unacknowledged) (The statement is presented as a factual claim about AI's activity in the introduction to the product section (p. 27), with no hedging.)
  • Implications: By framing AI as the entity 'pushing boundaries,' the text minimizes human agency in scientific discovery. It suggests that innovation is a technological inevitability rather than a human labor. This risks creating an 'automation bias' where users trust the system to innovate or find novel connections, not realizing the model is bounded by its training data. It also absolves developers of responsibility; if the AI is an autonomous pioneer 'pushing' limits, 'hallucinations' or errors can be framed as the cost of exploration rather than product defects.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The grammatical subject is 'Artificial intelligence,' framing the technology as the actor. This erases the engineers at Clarivate who designed the models, the researchers who generated the training data, and the library administrators deciding to deploy it. By granting agency to 'AI,' the text obscures the corporate strategy driving the deployment. It suggests the technology itself is the force of change, rather than the specific product development roadmap of the vendor.

3. The Conversational Partner​

Quote: "Enables users to uncover trusted library materials via AI-powered conversations."

  • Frame: Interface as interlocutor
  • Projection: This framing projects the human capacity for dialogue, mutual understanding, and social exchange onto a query-response interface. 'Conversation' implies two conscious entities exchanging meaning, maintaining context, and adhering to Gricean maxims of cooperation. A user inputs a prompt and the model generates a statistically probable token sequence; there is no 'conversation' because the system has no communicative intent, no model of the user's mind, and no understanding of the topic. This anthropomorphism encourages users to trust the system as a social peer rather than verify it as a search utility.
  • Acknowledgment: Direct (Unacknowledged) (The text treats 'conversations' as a literal description of the functional interaction with the software product (Summon Research Assistant).)
  • Implications: Framing database queries as 'conversations' is one of the most dangerous epistemic shifts in AI discourse. It encourages users to apply social heuristics (trust, politeness, assumption of truth-telling) to a statistical machine. Users are less likely to fact-check a 'conversational partner' than a 'search engine.' This creates liability ambiguity: if the 'partner' lies (hallucinates), is it a betrayal or a bug? It promotes a false sense of intimacy that can lead to over-reliance, particularly for students who may not distinguish between an authoritative librarian and a convincing text generator.

Accountability Analysis:

  • Actor Visibility: Named (actors identified)
  • Analysis: The text identifies the product 'Summon Research Assistant,' a Clarivate tool. However, the agency of the 'conversation' is displaced onto the tool itself. The analysis reveals that Clarivate designers chose to implement a chat interface (CUI) rather than a traditional query interface, thereby choosing to frame information retrieval as social interaction. This design choice, which increases engagement but potentially decreases critical distance, is presented as a natural feature.

4. The Trusted Associate​

Quote: "Clarivate helps libraries adapt with AI they can trust to drive research excellence"

  • Frame: Software as moral agent
  • Projection: Trust is a relational quality applicable to moral agents capable of betrayal, sincerity, and responsibility. Mapping 'trust' onto software creates a category error; software can be reliable, accurate, or robust, but it cannot be 'trustworthy' because it has no moral compass or ability to keep a promise. This metaphor projects human ethical standing onto the algorithmic system. It conflates the reliability of the brand (Clarivate) with the output of the stochastic model. It invites the reader to suspend skepticism, suggesting the AI has 'earned' a status that only human professionals can actually hold.
  • Acknowledgment: Direct (Unacknowledged) (The phrase 'AI they can trust' is used as a marketing claim, asserting the attribute of trustworthiness as an inherent property of the software.)
  • Implications: This is a critical instance of 'trust-washing.' By claiming the AI possesses the human quality of trustworthiness, the text attempts to bypass the necessary technical audit of accuracy and bias. If users believe the AI is 'trustworthy,' they may skip verification steps. This is particularly risky in academic research, where 'trust' implies peer review and epistemological rigor—processes a text generation model cannot perform. It shifts the burden of risk: if the 'trusted' AI fails, the user is left vulnerable because they were encouraged to lower their guard.

Accountability Analysis:

  • Actor Visibility: Named (actors identified)
  • Analysis: Clarivate explicitly names itself ('Clarivate helps libraries...'). However, the construction serves to transfer the company's reputational capital to the black-box algorithm. The decision-makers are the Clarivate executives and product managers who brand the system as 'trusted' despite the inherent probabilistic nature of LLMs. This framing serves the commercial interest of the vendor by positioning their proprietary AI as superior to 'untrusted' open models, commodifying 'trust' as a feature.

5. The Assistant Metaphor​

Quote: "ProQuest Research Assistant... Helps users create more effective searches, quickly evaluate documents"

  • Frame: Software as junior employee
  • Projection: The term 'Assistant' projects the role of a junior human employee—someone with limited authority but general competence and intent to help—onto the software. A human assistant understands the goal of a task; the software only matches patterns. This projection implies the system has a 'desire' to help and understands the context of the user's research. It obscures the fact that the 'assistant' is actually a data filter that creates dependencies. Unlike a human assistant who learns and can explain their reasoning, the software is opaque. This creates the illusion of labor without the presence of a mind.
  • Acknowledgment: Explicitly Acknowledged (The capitalization of 'Assistant' in the product names (e.g., 'ProQuest Research Assistant') marks it as a proper noun/title, formally acknowledging the role play.)
  • Implications: The 'Assistant' frame effectively lowers the user's expectations of authority (it's just an assistant) while simultaneously anthropomorphizing the interaction. This is a powerful rhetorical move for liability: an assistant can make mistakes that the 'boss' (user) must check. It subtly shifts responsibility for errors to the user while claiming the credit for efficiency. It also devalues the labor of actual library assistants, suggesting their complex cognitive work can be automated by a software feature, potentially impacting staffing decisions and labor valuation in libraries.

Accountability Analysis:

  • Actor Visibility: Named (actors identified)
  • Analysis: The product is named 'ProQuest Research Assistant,' owned by Clarivate. The metaphor masks the design decision to automate reference interview tasks. The specific human actors are the product teams who decided which 'assistant-like' behaviors to emulate. By framing it as an assistant, the vendor obscures the economic reality: they are selling an automated service to replace or augment human labor, directly serving the efficiency mandates mentioned elsewhere in the report.

6. Cognitive Facilitation​

Quote: "Facilitates deeper engagement with ebooks, helping students assess books’ relevance"

  • Frame: Algorithm as cognitive tutor
  • Projection: This metaphor projects the pedagogical skill of a teacher or tutor onto the algorithm. 'Engagement' and 'assessment' are complex cognitive and emotional processes. Suggesting an algorithm 'facilitates deeper engagement' implies it understands the semantic depth of the content and the student's learning state. In reality, the system likely summarizes text or highlights keywords. This anthropomorphizes the tool as a pedagogical agent that 'cares' about the depth of the student's learning, rather than a pattern-matching engine that reduces text to statistical summaries.
  • Acknowledgment: Direct (Unacknowledged) (The claim is presented as a functional description of the 'Ebook Central Research Assistant' without qualification.)
  • Implications: Claiming AI facilitates 'deeper engagement' creates a risk of 'cognitive offloading.' If the AI assesses relevance for the student, the student is not practicing the skill of assessment—they are outsourcing it. The implication is that the tool enhances learning, when mechanistically it may be bypassing the very cognitive struggle (reading, evaluating) required for deep learning. This framing sells a shortcut as an enhancement, potentially undermining the educational mission libraries strive to support.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The agent is the 'Ebook Central Research Assistant.' The human actors obscured are the developers who defined the metrics for 'relevance' and the UX designers who decided how 'engagement' is measured (likely clicks or time on page, not cognitive depth). Clarivate benefits from framing this data processing as 'pedagogical support,' aligning their product with the library's educational mission while concealing the reductionist nature of the technology.

7. The Strategic Mind​

Quote: "Web of Science Research Intelligence... Provides powerful analytics... to support decision-making"

  • Frame: System as intelligence officer
  • Projection: The name 'Research Intelligence' and the claim that it supports decision-making projects the quality of strategic insight onto data visualization tools. 'Intelligence' in this context invokes both military/state intelligence (gathering secrets) and cognitive capacity. It suggests the system extracts meaning and strategic value, whereas it actually aggregates metadata. This projects the human capacity for synthesis and strategic foresight onto a statistical aggregation tool. It implies the system 'knows' what is important for a decision.
  • Acknowledgment: Explicitly Acknowledged (The term 'Intelligence' is part of the product name, formally signaling the metaphorical frame of business/military intelligence.)
  • Implications: This framing promotes 'data-driven' governance where algorithmic outputs are treated as objective strategic insights. It risks replacing qualitative human judgment with quantitative metrics (h-indices, impact factors) laundered through the concept of 'Intelligence.' This can lead to policy decisions based on what is measurable rather than what is valuable. It inflates the authority of the dashboard, making it harder for human administrators to disagree with the 'Intelligence' provided by the system.

Accountability Analysis:

  • Actor Visibility: Named (actors identified)
  • Analysis: Clarivate is the named provider. The accountability analysis reveals that the 'intelligence' is actually a set of citation metrics defined by Clarivate's proprietary indices. The 'decision-making' support reinforces Clarivate's definitions of research value. The metaphor obscures the power dynamic: Clarivate sets the rules for what counts as 'impact,' and university leaders are encouraged to internalize these rules as objective 'intelligence' for their strategic decisions.

8. AI as Muscular Force​

Quote: "Academic libraries should leverage AI to strengthen student engagement"

  • Frame: AI as physical amplifier
  • Projection: The metaphors 'leverage' and 'strengthen' map physical mechanics (levers, muscle building) onto social and cognitive processes. This treats 'student engagement' not as a complex interpersonal state but as a load to be lifted or a muscle to be pumped up by the 'steroid' of AI. It projects a mechanistic causality: apply AI, get more engagement. It obscures the qualitative nature of engagement (interest, curiosity, belonging) which cannot be 'strengthened' by an algorithm in the same way a beam is strengthened by steel. It suggests a brute-force utility to the technology.
  • Acknowledgment: Direct (Unacknowledged) (Presented as a recommendation ('should leverage') treating the mechanic as a straightforward input-output relationship.)
  • Implications: This mechanistic framing reduces complex social problems (student disengagement) to technological optimization problems. It implies that if engagement is weak, the solution is more technology, not better pedagogy or more human support. It creates a policy bias toward purchasing tools rather than investing in people. It also sets up a false promise: if the tool is bought and engagement doesn't improve, it frames the failure as a failure of 'leverage' (implementation) rather than the tool's unsuitability for the task.

Accountability Analysis:

  • Actor Visibility: Hidden (agency obscured)
  • Analysis: The recommendation is directed at 'Academic libraries' (passive recipient) to use 'AI' (instrument). The agency of the vendors selling these engagement tools is hidden behind the imperative. The construction suggests that 'strengthening' is a natural result of the tool, obscuring the commercial interest of Clarivate in defining engagement in ways their tools can measure (e.g., login frequency vs. intellectual breakthrough).

Task 2: Source-Target Mapping​

About this task

For each key metaphor identified in Task 1, this section provides a detailed structure-mapping analysis. The goal is to examine how the relational structure of a familiar "source domain" (the concrete concept we understand) is projected onto a less familiar "target domain" (the AI system). By restating each quote and analyzing the mapping carefully, we can see precisely what assumptions the metaphor invites and what it conceals.

Mapping 1: Human Conversation (Interlocutor) → Large Language Model Prompt-Completion Loop​

Quote: "Enables users to uncover trusted library materials via AI-powered conversations."

  • Source Domain: Human Conversation (Interlocutor)
  • Target Domain: Large Language Model Prompt-Completion Loop
  • Mapping: The mapping transfers the structure of human social interaction—turn-taking, shared context, Gricean maxims of cooperation, and intent to communicate—onto the statistical process of token generation. It assumes the AI 'partner' is listening, understanding, and responding with communicative intent. It implies a relationship of reciprocity where both parties are working toward a shared goal of truth-finding.
  • What Is Concealed: This mapping conceals the autistic nature of the mechanism: the model creates outputs based on probability distributions of training data, not an understanding of the user's query. It hides the lack of a 'self' or 'memory' outside the immediate context window. Crucially, it obscures the reality that the 'conversation' is a user interface design choice masking a database query, potentially leading users to anthropomorphize the source of the data and miss hallucinations.
Show more...

Mapping 2: Moral/Social Contract (Trust) → Software Reliability and Verification​

Quote: "Clarivate helps libraries adapt with AI they can trust"

  • Source Domain: Moral/Social Contract (Trust)
  • Target Domain: Software Reliability and Verification
  • Mapping: This maps the complex social and emotional bonds of trust between people (based on shared values, accountability, and history) onto the technical performance of a software product. It assumes the software has 'character' or 'integrity.' It invites the user to feel safe and lower their defenses, treating the software as a vetted member of the community rather than a tool.
  • What Is Concealed: It conceals the statistical error rates, the bias in training data, and the lack of moral agency in the system. You cannot 'trust' an algorithm; you can only verify its performance specifications. This metaphor hides the proprietary nature of the 'trust': users are asked to trust Clarivate's black box without being able to inspect the weights or training data that would allow for actual verification.

Mapping 3: Pioneer/Explorer (Physical Agent) → Algorithmic Data Processing​

Quote: "Artificial intelligence is pushing the boundaries of research"

  • Source Domain: Pioneer/Explorer (Physical Agent)
  • Target Domain: Algorithmic Data Processing
  • Mapping: This maps the human qualities of curiosity, ambition, and physical exertion ('pushing') onto the passive execution of code. It assumes the AI has its own momentum and directionality, independent of human operators. It frames the technology as the active subject of history, driving progress forward through its own inherent capability.
  • What Is Concealed: It conceals the human labor of the researchers who actually push boundaries, and the engineers who design the tools. It hides the dependency of the AI on existing data (it cannot push boundaries beyond its training distribution without hallucinating). It masks the economic forces driving the deployment of these tools, presenting their expansion as a natural technological evolution rather than a market strategy.

Mapping 4: Junior Employee (Assistant) → Information Retrieval Algorithm​

Quote: "ProQuest Research Assistant... Helps users create more effective searches"

  • Source Domain: Junior Employee (Assistant)
  • Target Domain: Information Retrieval Algorithm
  • Mapping: This maps the role of a subordinate human worker—who has limited authority but general competence and helpful intent—onto a specific software function. It assumes the software shares the user's goals and is working 'for' them. It implies a hierarchical relationship where the user is the boss and the AI is the tireless worker.
  • What Is Concealed: It conceals the lack of intent; the software does not 'want' to help. It conceals the specific mechanisms of query expansion and ranking that define 'effective.' It hides the fact that the 'assistant' is actually constraining the search to Clarivate's licensed content ecosystem. It also conceals the displacement of human library assistants who formerly provided this help with genuine understanding.

Mapping 5: Professional Visionary → Blog/Report/Concept​

Quote: "The Digital Librarian points to the future"

  • Source Domain: Professional Visionary
  • Target Domain: Blog/Report/Concept
  • Mapping: The 'Digital Librarian' is personified as a visionary leader pointing the way. This maps the human capacity for foresight and leadership onto a concept or a digital trend. It implies that the technology itself has a vision for the profession's future.
  • What Is Concealed: It conceals the specific authors and corporate interests behind 'The Digital Librarian' concept. It hides the fact that the 'future' being pointed to is one that benefits technology vendors. It obscures the alternative futures that human librarians might envision which do not center on purchasing more AI products.

Mapping 6: Teacher/Facilitator → User Interface Feature (Summarization/Highlighting)​

Quote: "AI... facilitate deeper engagement with ebooks"

  • Source Domain: Teacher/Facilitator
  • Target Domain: User Interface Feature (Summarization/Highlighting)
  • Mapping: This maps the pedagogical skill of a teacher facilitating a seminar onto a software feature. It assumes the software understands what 'depth' means in an intellectual context and can guide a student toward it. It implies the tool is an active participant in the learning process.
  • What Is Concealed: It conceals the reductionist nature of the tool—likely providing summaries or extracting keywords, which might actually encourage shallower engagement (skimming) rather than deep reading. It hides the algorithmic definition of 'engagement' (time on task, clicks) which differs from the pedagogical definition (critical reflection).

Mapping 7: Biological Organism → Institutional Metrics​

Quote: "Pulse of the Library"

  • Source Domain: Biological Organism
  • Target Domain: Institutional Metrics
  • Mapping: This maps the autonomic biological functions of a living body onto the operations of an institution. It assumes the library has a singular health status that can be diagnosed. It implies a natural cycle of life that requires monitoring.
  • What Is Concealed: It conceals the fractured, political nature of library systems (comprised of conflicting stakeholders). It hides the fact that the 'pulse' is actually a survey construction—a data artifact created by the surveyor (Clarivate), not a natural phenomenon waiting to be found. It obscures the structural causes of 'poor health' (austerity) by focusing on symptoms.

Mapping 8: Cognitive/Military Intelligence → Citation Analytics​

Quote: "Web of Science Research Intelligence"

  • Source Domain: Cognitive/Military Intelligence
  • Target Domain: Citation Analytics
  • Mapping: This maps the high-level cognitive capacity for understanding and strategy onto a database of citation links. It assumes the data contains inherent 'wisdom' or strategic insight. It implies that possessing this data equates to being intelligent.
  • What Is Concealed: It conceals the bias in citation databases (English-language dominance, STEM bias). It hides the fact that 'intelligence' here is just a count of references, not an understanding of content. It obscures the proprietary algorithms that calculate 'impact,' forcing libraries to accept Clarivate's definition of value.

Task 3: Explanation Audit (The Rhetorical Framing of "Why" vs. "How")​

About this task

This section audits the text's explanatory strategy, focusing on a critical distinction: the slippage between "how" and "why." Based on Robert Brown's typology of explanation, this analysis identifies whether the text explains AI mechanistically (a functional "how it works") or agentially (an intentional "why it wants something"). The core of this task is to expose how this "illusion of mind" is constructed by the rhetorical framing of the explanation itself, and what impact this has on the audience's perception of AI agency.

Explanation 1​

Quote: "Artificial intelligence is pushing the boundaries of research and learning. Clarivate helps libraries adapt with AI they can trust..."

  • Explanation Types:

    • Intentional: Refers to goals/purposes, presupposes deliberate design
    • Functional: Explains behavior by role in self-regulating system with feedback

  • Analysis (Why vs. How Slippage): This passage uses a hybrid Intentional/Functional framing. AI is framed intentionally as an agent 'pushing' boundaries (active goal), while Clarivate is the functional stabilizer helping libraries 'adapt.' This choice emphasizes the inevitability of AI—it is a force with its own momentum—while obscuring the mechanical reality that AI is a tool being deployed by humans. By framing AI as the agent pushing, it removes responsibility from the developers pushing the technology. It creates a narrative where libraries are reactive subjects who must 'adapt' to the will of the technology.

  • Consciousness Claims Analysis: The passage projects agency but avoids explicit consciousness verbs, relying instead on physical metaphors ('pushing'). However, 'trust' implies a knowledge claim—that the system possesses a reliability character trait. The claim 'AI they can trust' is an epistemic shortcut, asking the reader to accept the system's outputs as true/valid without explaining how the system ensures this. It completely ignores the mechanistic reality of probabilistic generation, substituting a brand promise for technical description. It creates a 'curse of knowledge' dynamic where the vendor's assertion of reliability is substituted for the user's need to verify.

  • Rhetorical Impact: This framing creates a sense of urgency and dependency. If AI is 'pushing boundaries' on its own, the library has no choice but to keep up. Clarivate positions itself as the necessary safety harness ('adapt with AI they can trust') against this autonomous force. It encourages a relationship of reliance rather than control, diminishing the library's agency to reject or reshape the technology.

Show more...

Explanation 2​

Quote: "Summon Research Assistant: Enables users to uncover trusted library materials via AI-powered conversations."

  • Explanation Types:

    • Functional: Explains behavior by role in self-regulating system with feedback
    • Intentional: Refers to goals/purposes, presupposes deliberate design

  • Analysis (Why vs. How Slippage): The explanation is primarily functional ('enables users to uncover'), describing the tool's role. However, 'AI-powered conversations' introduces an Intentional frame, implying the AI is a communicative agent. This choice emphasizes the ease of use (conversation) while obscuring the search mechanism. It frames the interaction as social rather than technical. The 'why' of the result is hidden behind the 'who' of the conversational partner.

  • Consciousness Claims Analysis: The phrase 'AI-powered conversations' is a strong anthropomorphic projection. While it doesn't use verbs like 'thinks,' 'conversation' presupposes a mutual exchange of meaning. This implies the system understands the user's intent. Mechanistically, the system is converting user text to vector embeddings and retrieving similar vectors. There is no conversation. The text bypasses this technical reality to sell a user experience fantasy. It asks the user to accept the interface metaphor as the mechanism.

  • Rhetorical Impact: This framing shapes the user to view the AI as a collaborator. It increases trust but also risk. Users are less likely to question a 'conversational partner' than a 'search query.' It reduces the perceived autonomy of the user (who is now 'conversing' rather than 'commanding') and creates a risk of emotional manipulation or over-reliance on the machine's 'voice.'

Explanation 3​

Quote: "The Digital Librarian points to the future of computer literacy, considering AI’s impact on critical evaluation..."

  • Explanation Types:

    • Theoretical: Embeds in deductive framework, may invoke unobservable mechanisms
    • Reason-Based: Gives agent's rationale, entails intentionality and justification

  • Analysis (Why vs. How Slippage): This passage uses a Theoretical frame (citing a concept/report 'The Digital Librarian') to explain the 'why' of future literacy. It frames the abstract concept as an agent 'pointing' the way. This emphasizes a specific vision of the future (AI-centric) as an objective theoretical reality. It obscures the commercial interests defining this 'future.' The 'Digital Librarian' is presented as a reasoned authority, not a marketing construct.

  • Consciousness Claims Analysis: This passage attributes the human capacity for foresight ('points to the future') to a text/concept. It avoids direct consciousness verbs but implies a knowing subject ('The Digital Librarian') that understands the trajectory of history. Mechanistically, this is a citation of a report, but rhetorically, it functions as an appeal to authority. It projects understanding onto the discourse itself, validating the report's conclusions as independent of the author's bias.

  • Rhetorical Impact: This framing constructs authority. By personifying the trend/report as 'The Digital Librarian,' it creates a unified figurehead for the movement. It creates a sense of inevitability—the Digital Librarian has spoken. This reduces the space for critique; to disagree is to be against the 'future' pointed to by this figure. It encourages compliance with the suggested upskilling and adoption mandates.

Explanation 4​

Quote: "Academic libraries should leverage AI to strengthen student engagement, research excellence and discovery."

  • Explanation Types:

    • Functional: Explains behavior by role in self-regulating system with feedback

  • Analysis (Why vs. How Slippage): This is a purely Functional explanation. AI is a tool to perform a function (strengthen engagement). It frames the 'how' as a simple input-output operation (leverage -> strengthen). This emphasizes utility and obscures complexity. It treats 'engagement' as a variable that can be mechanically increased, obscuring the human/social reasons why engagement might be low. It frames AI as a solution to a functional deficit.

  • Consciousness Claims Analysis: This passage is mechanistically reductive. It avoids consciousness claims but makes a strong causal claim: AI can strengthen engagement. This assumes the system 'knows' how to engage students. Mechanistically, the tools likely provide notifications, chatbots, or recommendations. The text implies these outputs equate to human 'engagement.' It avoids technical description of what the AI actually does (e.g., sends automated emails) to maintain the high-level promise of 'strengthening.'

  • Rhetorical Impact: This framing appeals to administrative efficiency. It suggests complex problems have purchaseable solutions. It reduces the perceived risk of AI (it's just a lever) and increases the perceived autonomy of the administrator (you can pull the lever). However, it sets up potential failure: if the lever doesn't work, the administrator failed to 'leverage' it correctly. It commodifies student engagement.

Explanation 5​

Quote: "Facilitates deeper engagement with ebooks, helping students assess books’ relevance and explore new ideas."

  • Explanation Types:

    • Functional: Explains behavior by role in self-regulating system with feedback
    • Reason-Based: Gives agent's rationale, entails intentionality and justification

  • Analysis (Why vs. How Slippage): This mixes Functional (facilitates) with Reason-Based (helping students assess). It explains the AI's behavior by its helpful purpose. This emphasizes the benevolent role of the technology. It obscures the fact that 'assessing relevance' is the core cognitive task of the student. By framing the AI as doing this, it reframes a cognitive shortcut as 'help.' It justifies the automation of critical thinking as a service.

  • Consciousness Claims Analysis: This passage attributes a high-level cognitive capability (assessing relevance) to the system. While 'facilitates' is a process verb, 'helping assess' implies the system understands the criteria for relevance. Mechanistically, the system is performing keyword matching or semantic similarity scoring. It does not 'know' the book or the student's needs. The text projects the outcome (student finds book) onto the intent of the machine.

  • Rhetorical Impact: This framing makes the tool appear indispensable for education. It reframes a search tool as a 'learning partner.' It encourages trust in the algorithm's ranking. If the AI says a book is relevant, the student believes it. This erodes the student's own agency in evaluating sources, training them to rely on the 'Assistant.' It constructs a market for tools that do the thinking for the user.

Task 4: AI Literacy in Practice - Reframing Anthropomorphic Language​

About this task

This section proposes alternative language for key anthropomorphic phrases, offering more mechanistic and precise framings that better reflect the actual computational processes involved. Each reframing attempts to strip away the projections of intention, consciousness, or agency that are embedded in the original language.

V3 Enhancement: A fourth column addresses human agency restoration—reframing agentless constructions to name the humans responsible for design and deployment decisions.

Original Anthropomorphic FrameMechanistic ReframingTechnical Reality CheckHuman Agency Restoration
Artificial intelligence is pushing the boundaries of research and learning.New algorithmic methods allow researchers to process larger datasets and identify statistical correlations previously computationally too expensive to detect.AI models do not 'push' or have ambition; they execute matrix multiplications on provided data. The 'pushing' is done by human researchers applying these calculations.Clarivate's engineering teams and academic researchers are using machine learning to expand the scope of data analysis in research.
Clarivate helps libraries adapt with AI they can trustClarivate provides software tools with verified performance metrics and established error rates to assist libraries in data management.Models cannot be 'trusted' (a moral quality); they function with probabilistic accuracy that must be audited. 'Trust' here refers to vendor reputation, not algorithmic intent.Clarivate executives market these tools as reliable based on internal testing protocols.
Enables users to uncover trusted library materials via AI-powered conversations.Allows users to retrieve database records using a natural language query interface that generates text responses based on retrieved metadata.The system does not 'converse'; it tokenizes user input, retrieves documents, and generates a probable text sequence summarizing them.Clarivate designers implemented a chat interface to replace the traditional keyword search bar.
ProQuest Research Assistant... Helps users create more effective searchesThe ProQuest query optimization algorithm suggests keywords and filters to narrow search results based on citation density.The system does not 'help' (social act); it filters data. 'Effective' refers to statistical relevance ranking, not semantic understanding.Clarivate developers programmed the system to prioritize specific metadata fields to refine user queries.
Facilitates deeper engagement with ebooks, helping students assess books’ relevanceThe software extracts and displays high-frequency keywords and summary fragments to allow rapid content scanning.The system calculates semantic similarity scores; it does not 'assess relevance' or facilitate 'engagement' (which is a cognitive state of the user).Product designers chose to highlight key passages to reduce the time students spend evaluating texts.
AI to strengthen student engagementUse automated notification and recommendation algorithms to increase the frequency of student interaction with library platforms.AI cannot 'strengthen' social engagement; it maximizes interaction metrics (clicks/logins) based on reward functions.University administrators are using Clarivate tools to attempt to increase student retention metrics.
Librarians recognize that learning doesn’t happen by itself.Librarians understand that acquiring new skills requires allocated time, funding, and structured curriculum.N/A - This quote accurately attributes cognition to humans, though it uses the passive 'happen by itself' to obscure the need for management to pay for it.Librarians argue that management must fund training programs rather than expecting staff to upskill on their own time.
Pulse of the LibrarySurvey Statistics on Library Operations and sentiment.There is no biological 'pulse'; these are aggregated data points from a voluntary survey sample.Clarivate researchers analyzed survey responses to construct a snapshot of current trends.

Task 5: Critical Observations - Structural Patterns​

Agency Slippage​

The text systematically oscillates between agency attributed to librarians and agency attributed to AI. In the survey findings (pp. 9-26), librarians are the agents: they 'explore,' 'implement,' and 'feel.' However, when the text pivots to the product section (p. 27), agency slips to the technology: 'AI is pushing boundaries,' 'Assistants help,' 'Intelligence supports.' This slippage serves a rhetorical function. It establishes the library as a site of struggle and anxiety (human agency is limited by budget/skills), and then presents AI as the confident, capable agent that steps in to resolve the deficit. The 'curse of knowledge' appears where the vendor's understanding of the tool's function is projected onto the tool itself—because the designers intended it to help, the text says the AI 'helps.' Agentless constructions like 'adoption... continues apace' hide the corporate marketing driving this adoption. The slippage enables the claim that libraries 'must' adapt to an external force, rather than choosing to buy a product.

Metaphor-Driven Trust Inflation​

The document relies heavily on relation-based trust metaphors to market statistical products. The central metaphor is the 'Assistant' and the 'Partner.' By branding products as 'Research Assistants' and claiming libraries can 'trust' the AI, Clarivate moves the basis of evaluation from performance (accuracy rates, recall) to relationship (fidelity, help). This is critical because AI systems are statistically unreliable; framing them as 'trusted partners' encourages users to overlook 'hallucinations' as one might forgive a colleague's error. The text contrasts the 'nervousness' of librarians (p. 9) with the 'trust' offered by the tool (p. 27), implying that the solution to human anxiety is technological intimacy. This constructs authority not through technical proof, but through the assurance of a 'trusted brand' embedding itself in the machine.

Obscured Mechanics​

The anthropomorphic language completely conceals the mechanical and economic realities of the systems. The 'name the corporation' test reveals that 'AI' is frequently a stand-in for 'Clarivate's products.' The metaphors of 'conversations' and 'engagement' hide the technical reality of token prediction and vector search. Crucially, the text obscures the source of the 'Intelligence.' Is it based on Clarivate's proprietary Web of Science index? If so, the 'intelligence' is biased toward high-impact journals, erasing marginalized knowledge. The 'Assistant' metaphor hides the labor displacement; it doesn't say 'this script automates reference desk tasks,' it says it 'helps users.' This obscures the potential for administrative decisions to cut staff based on the tool's capabilities. Transparency regarding training data, privacy trade-offs, and error rates is absent, replaced by the high-level assurance of 'trust.'

Context Sensitivity​

Anthropomorphism is strategically distributed. In the 'Risks' section (p. 6, 18), the language is abstract and passive ('privacy concerns,' 'budget constraints'). However, in the 'Solutions/Products' section (p. 27-28), the language becomes aggressively agential and anthropomorphic ('AI pushing boundaries,' 'Assistant enables,' 'Intelligence supports'). This asymmetry creates a world where problems are structural/environmental, but solutions are agentic/technological. The technical grounding is minimal; there is no discussion of how the 'Generative AI' works, only what it 'does' for the user. The intensity of the 'Assistant' metaphor in the product catalog serves to naturalize the software as a member of the workforce, making the purchase decision feel like hiring a reliable employee rather than licensing software.

Accountability Synthesis​

Accountability Architecture

This section synthesizes the accountability analyses from Task 1, mapping the text's "accountability architecture"—who is named, who is hidden, and who benefits from obscured agency.

The text constructs an 'accountability sink' where the benefits of AI are attributed to the 'Assistant' (the product), but the challenges are attributed to the environment (budgets, geopolitics). Human agency is displaced in two ways: (1) The 'inevitability' of AI adoption ('pushing boundaries') absolves administrators of the choice to not adopt. (2) The framing of AI as a 'partner' diffuses liability for errors. If the 'Assistant' makes a mistake, it is a collaboration failure, not a product defect. The 'name the actor' test shows that Clarivate is the primary beneficiary of this displacement. By positioning AI as a 'trusted' agent, they invite libraries to offload responsibility for research integrity onto the tool ('AI to drive research excellence'). If the tool fails, the library is left holding the bag for 'mismanaging' the partner. The text obscures the fact that Clarivate is selling the very disruption it claims to help libraries 'adapt' to.

Conclusion: What This Analysis Reveals​

The Core Finding

Two dominant anthropomorphic patterns anchor this text: the 'AI as Collaborative Agent' (Assistant, Partner, Conversationalist) and the 'AI as Autonomous Force' (Pushing boundaries, Innovation wave). These patterns form a mutually reinforcing system. The 'Autonomous Force' metaphor creates the crisis: AI is moving fast, pushing boundaries, and creating an environment libraries must survive ('pulse'). The 'Collaborative Agent' metaphor offers the solution: Clarivate's 'Assistants' and 'Trusted AI' help the library adapt to this force. The foundational assumption is that AI possesses agency—it acts upon the world. The consciousness architecture supports this by attributing 'trustworthiness' and 'intent to help' to the software, masking the commercial logic of the vendor. Without the 'Assistant' metaphor, the product is simply a search filter; the metaphor is load-bearing for the value proposition.

Mechanism of the Illusion:​

The illusion of mind is constructed through a 'bait-and-switch' of agency. The text begins with human anxieties (librarians' nervousness, budget fears), validating the reader's emotional state. It then introduces AI not as a tool that requires more human work, but as a 'partner' that shares the load. The 'curse of knowledge' operates powerfully in the product descriptions: the designers know the tool is meant to help, so they name it 'Assistant.' This label leads the audience to attribute the mind of an assistant to the code. The temporal structure matters: the report establishes the 'problem' (rapid change, complexity) before introducing the 'Assistant' (p. 27) as the hero. This narrative arc exploits the audience's desire for relief from administrative pressure, making them vulnerable to the illusion that the software 'cares' about their mission.

Material Stakes:​

Categories: Economic, Epistemic, Institutional

The material stakes of this framing are significant. Economically, the 'Assistant' metaphor obscures labor displacement. If administrators believe the software functions as a 'Research Assistant,' they may justify freezing hiring for human reference librarians, replacing salaries with license fees paid to Clarivate. Epistemically, the 'Conversational Partner' and 'Trusted AI' frames degrade research rigor. If students and researchers view the AI as a 'knower' to be conversed with rather than a text generator to be audited, the verification standard drops, allowing hallucinations to enter the scholarly record. Institutionally, the 'Autonomous Force' metaphor creates policy paralysis. If AI is 'pushing boundaries' inevitably, libraries may cease resisting surveillance capitalism or data enclosure, accepting proprietary 'black boxes' as the price of survival. The winner is the vendor (Clarivate) who captures budget and data; the losers are the library workers whose labor is devalued and the patrons whose privacy and epistemic standards are compromised.

AI Literacy as Counter-Practice:​

Countering these risks requires a rigorous practice of mechanistic reframing. Replacing 'AI knows' with 'model retrieves' breaks the illusion of the 'Assistant' and reveals the dependency on data quality. Reframing 'AI pushing boundaries' to 'Corporations deploying algorithms' restores the site of political contestation. Precision is resistance because it forces the recognition that the 'mind' in the machine is an illusion and the 'help' is a commercial service. Resistance to this literacy comes from vendors like Clarivate, whose value proposition relies on the 'magic' of the Assistant metaphor to justify high costs. It also comes from overwhelmed administrators who want to believe a technological solution exists for their structural problems. Adopting precise language forces libraries to confront the hard reality that technology cannot solve the crisis of funding or the complexity of learning.

Path Forward​

The discourse future forks here. In a 'Mechanistic Precision' future, journals and institutions mandate that AI be described as 'probabilistic text generation' rather than 'assistants.' This vocabulary makes the limitations visible, protecting epistemic standards but potentially dampening the 'hype' needed for funding. In an 'Anthropomorphic Deepening' future, the 'Assistant' metaphor becomes literalized; legal and ethical frameworks grant 'trust' to agents, eroding human accountability. A 'Status Quo' future maintains the confusion, allowing vendors to exploit the ambiguity. The desirable path for libraries involves 'Critical Technical Literacy': using mechanistic language to describe operations ('the model predicts') while reserving agentic language for the humans who design, deploy, and audit the systems. This ensures that 'trust' remains a human-to-human pact, not a user-to-interface delusion.

Extended Processing Summary​

Gemini's Processing Steps
What you are about to read…

Gemini refers to the text below as "thought summaries." This is an overt consciousness projection because 'intentions' are hallmarks of a conscious mind that 'knows' what it is doing and why. The concealed mechanistic process is probabilistic text generation. Treat this as just another rhetorical artifact—a way of making the model's processing legible. The first-person framing of these "thought summaries" is a presentation choice for the user-facing output, not a window into "real" thoughts. These are computational artifacts, not cognitive reports from a quirky, curious or conflicted mind.

Defining the Analysis Focus

I'm currently zeroing in on the request, clarifying my role as a critical discourse analyst examining metaphorical and anthropomorphic language within the "Pulse of the Library 2025" PDF. My task is to pinpoint specific instances of this language and analyze its implications, particularly in relation to the evolving role of libraries in a future-focused context.

Framing the Analytical Lens

I've been drilling down on the conceptual underpinnings, integrating insights from Lakoff & Johnson, Brown, and CDA. I'm focused on the tension between human "knowing" and machine "processing," highlighting instances of agency displacement. The output will be a single valid JSON object adhering to a precise schema.

Examining Metaphorical Instances

I'm now focusing on specific metaphorical instances from the document, particularly those related to AI. I've identified several examples, including AI as a conversational partner, a trusted entity, a benevolent helper, and a boundary-pusher. The focus is on the language used to describe AI's capabilities, particularly where agency or emotional qualities are attributed to the technology. I'm exploring the implications of these attributions on how we perceive and interact with AI in a library context.

Pinpointing Concealed Implications

I'm now deeply analyzing the source-target mappings in the document. I've broken down "AI-powered conversations," "AI they can trust," and the "Research Assistant" product name, revealing the concealed aspects of these metaphors. The first conceals statistical prediction, the second masks data dependency, and the third hides the lack of critical thinking. My focus now is on extracting these details accurately. I'm moving on to analyzing the "Explanation Audit" using Brown's typology, starting with the intentional/functional attribution to AI's actions.

Deconstructing Metaphors Further

I'm now focusing on specific passages and their implications. Passage 3 highlights investment as the driving force behind AI opportunities, linking agency to financial decisions. Passage 4 uses the "Digital Librarian" metaphor to represent a future-oriented role, suggesting a human-machine hybrid. Passage 5 attributes deeper engagement to AI. I'm also analyzing the reframed language from Task 4, contrasting the original metaphors with more literal descriptions. The current focus is the agent/action/object relationship in relation to AI.

Evaluating Implied Agency

I'm now zeroing in on instances where agency is implicitly assigned. I'm noting the contrast between "Assistants" in the product section and "challenges/risks" in the survey, revealing an interesting dynamic. "AI adoption" is presented as inevitable, while "Budget cuts" are framed as a passive occurrence. The focus is on Clarivate's positioning as a solution provider to problems their technology creates, emphasizing the need for critical analysis of these implied agents and their actions.

Analyzing Language Choices

I'm now zeroing in on the document's careful wording. It uses "AI tools" frequently, avoiding stronger anthropomorphic language. However, subtle instances persist, like attributing agency to AI through verbs ("pushing boundaries," "facilitates"). I'm also examining how these linguistic choices shape the perception of AI's role and capabilities within the library setting. The current focus is on the impact of embedded metaphors, like "Research Assistant," on users' understanding.

Refining Agency Analysis

I'm presently focusing on how Clarivate positions its products, particularly the shift from librarians addressing issues to AI assistants offering help, which I am scrutinizing. Furthermore, I'm examining agency within the report: how AI is presented as an external force requiring adaptation, with Clarivate as the essential intermediary. I'm also exploring the "trusted citation index" metaphor and the complete omission of the underlying mechanics of these AI systems. I am ensuring that the JSON output is perfect, with precise enums, correct word counts, and proper JSON syntax.

Verifying Metaphorical Accuracy

I'm now methodically verifying the AI quotes for strict agency verbs. I'm ensuring accuracy with the chosen verbs and avoiding over-interpretation. The goal is a precise and reliable analysis. My JSON output is almost complete; it should have everything.

Analysis Provenance

Run ID: 2025-12-23-pulse-of-the-library-2025-metaphor-pu415f Raw JSON: 2025-12-23-pulse-of-the-library-2025-metaphor-pu415f.json Framework: Metaphor Analysis v6.4 Schema Version: 3.0 Generated: 2025-12-23T21:03:16.652Z

Discourse Depot © 2025 by TD is licensed under CC BY-NC-SA 4.0