Artificially intelligent conversational agents in libraries
Bibliographic record
Abstract
Purpose Conversational agents are natural language interaction interfaces designed to simulate conversation with a real person. This paper seeks to investigate current development and applications of these systems worldwide, while focusing on their availability in Canadian libraries. It aims to argue that it is both timely and conceivable for Canadian libraries to consider adopting conversational agents to enhance – not replace – face‐to‐face human interaction. Potential users include library web site tour guides, automated virtual reference and readers' advisory librarians, and virtual story‐tellers. To provide background and justification for this argument, the paper seeks to review agents from classic implementations to state‐of‐the‐art prototypes: how they interact with users, produce language, and control conversational behaviors. Design/methodology/approach The web sites of the 20 largest Canadian libraries were surveyed to assess the extent to which specific language‐related technologies are offered in Canada, including conversational agents. An exemplified taxonomy of four pragmatic purposes that conversational agents currently serve outside libraries – educational, informational, assistive, and socially interactive – is proposed and translated into library settings. Findings As of early 2010, artificially intelligent conversational systems have been found to be virtually non‐existent in Canadian libraries, while other innovative technologies proliferate (e.g. social media tools). These findings motivate the need for a broader awareness and discussion within the LIS community of these systems' applicability and potential for library purposes. Originality/value This paper is intended for reflective information professionals who seek a greater understanding of the issues related to adopting conversational agents in libraries, as this topic is scarcely covered in the LIS literature. The pros and cons are discussed, and insights offered into perceptions of intelligence (artificial or not) as well as the fundamentally social nature of human‐computer interaction.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.004 | 0.007 |
| Scholarly communication | 0.007 | 0.004 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".