Cited by 64Web and Library ServicesAI in Service InteractionsLibrary Science and Information Literacy

Implementing a Chatbot on a Library Website

Ehrenpreis, Michelle, DeLooper, J.·2022·Journal of Web Librarianship

Abstract

A library’s website is a virtual point of contact for interacting with its patrons. Ensuring a library’s website has easily findable content is critical for providing access to library resources and highlighting services and events. One tool for assisting with content findability is a chatbot, a form of artificial intelligence software. In this case study, Lehman College’s Leonard Lief Library implemented Ivy, a proprietary educational software chatbot on its website, the first of its kind for an academic library. This chatbot functioned as a new tool that assisted users seeking information and provided insight to librarians about the kinds of topics students search for via the library website. This article provides the first detailed description in the literature of an implementation of a proprietary chatbot for an academic library.

Integrity signals

Registry

Crossref · 10.1080/19322909.2022.2060893

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Most current chatbots in academic libraries have primarily conversational, summarization and on demand assistance roles.

    “Unlike the primarily conversational, summarization and on demand assistance roles of most current chatbots in academic libraries (Ehrenpreis & DeLooper, 2022;Verma, 2023),”
  • Ehrenpreis & DeLooper (2022) explore how their library prioritized privacy considerations in AI tools and services, through working with a chatbot vendor to adjust privacy settings.

    “Additionally, Ehrenpreis & DeLooper (2022) explore how “their library prioritized privacy considerations in AI tools and services, through working with a chatbot vendor to adjust privacy settings” (as cited in Mannheimer et al., 2024, p. 23).”

    From The Rise of Artificial Intelligence in Academic Libraries (2025) · cites this paper as Ehrenpreis & DeLooper, 2022

  • The vendor agreed to avoid tracking users' IP addresses, but it took months and in the meantime patrons' IP addresses were still visible on transcripts.

    “The vendor agreed to this, but it took months and, in the meantime, patrons' IP addresses were still visible on transcripts (p.136).”

    From The Rise of Artificial Intelligence in Academic Libraries (2025) · cites this paper as Ehrenpreis & DeLooper, 2022

  • AI privacy concerns conflict with the ALA's value of privacy as evidenced by the Ehrenpreis & DeLooper (2022) example in which Ivy was tracking its users' IP addresses.

    “Also, AI privacy concerns conflict with the ALA's value of privacy as evidenced by the Ehrenpreis Ehrenpreis & DeLooper (2022) example in which Ivy was tracking its users' IP addresses (p.136).”

    From The Rise of Artificial Intelligence in Academic Libraries (2025) · cites this paper as Ehrenpreis & DeLooper, 2022

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Ehrenpreis, M., & DeLooper, J.
Affiliations
Lehman College (US)
Corresponding author
Ehrenpreis, Michelle
Venue
Journal of Web Librarianship
Published
2022-04-03
Volume
16
Issue
2
Pages
120-142
ISSN
  • 1932-2909 (ISSN-L)
  • 1932-2917
OpenAlex
W4226334290
Cited by
64
References
14
Citations by year
2026: 18 · 2025: 17 · 2024: 15 · 2023: 13 · 2022: 1
FWCI
11.38
Type
journal article
Language
en
Open access
closed
Locations
  • Journal of Web Librarianship (publishedVersion)
  • CUNY Academic Works (City University of New York) (submittedVersion)
Topics
  • Physical Sciences › Computer Science › Information Systems › Web and Library Services
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
  • Social Sciences › Library and Information Sciences › Library Science and Information Literacy
Keywords
chatbots, library websites, academic libraries, user search behavior, library user services

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review