Artificially intelligent conversational agents in libraries

Abstract

PurposeConversational 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/approachThe 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.FindingsAs 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/valueThis 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.

Emerging trends in knowledge organization and information organization course curriculum

“…In our KO curricula, I argue, increased prominence should be given to the appreciation and research into language, its use, structure, and its automated analyses. Looking beyond both the 19th and 20th century paradigms, libraries are likely to consider incorporating more language technologies beyond now standard search capabilities, such as conversational agents (Rubin, Thorimbert, and Chen, 2010 Dr. Pattuelli will discuss the results of a recent investigation she conducted on the current state of knowledge organization education in ALA-accredited schools of library and information science. The study examined the subject content of knowledge organization courses taught in 57 ALA-accredited LIS programs and was based on a pilot study conducted on the ten top-ranked ten LIS schools.…”

Virtual Assistants for the Cultural Heritage Domain

“…Other general applications of virtual assistants are in the area of education for instructions and learning [8], delivering information from large data sets like encyclopedias in libraries [9], for informational purposes in e-commerce [10], merging heterogeneous data using multi-agent conversational agents [11], tourism [12], and several others.…”

Student responses to an animated character in information literacy instruction

“…Authors have posited ways ECAs (also called avatars) might be used in libraries (Balleste, 2007;Rubin et al, 2010). Despite this theoretical interest, reviews of the relevant library literature by Rubin et al (2010) and Liu (2011) found that implementation is rare. One exception, identified by Liu, is Neva, an embodied conversational agent available on kiosks in the McLuhan Documentation Center at the University of Lubeck.…”