Conversations Over Clicks: Impact Of Chatbots On Information Search In Interdisciplinary Learning

Hannah Kim, Temple University

Sergei L. Kosakovsky Pond, Temple University

Date

01/2026

AI Overview

Why it matters

As students increasingly shift from traditional tutorials to generative AI chatbots for help, understanding how conversational agents change their ability to find relevant information in complex, interdisciplinary learning environments is essential.

Study at a glance

Question: How do generative AI chatbot interactions influence a learner's information search behaviors and cues?
Setting and data: Temple University, single doctoral student researcher-practitioner studying bioinformatics, March 21 to April 3, 2025, analyzing 92 queries across 6 transcripts and 6 journals.
Method: Mixed-methods autoethnographic study using thematic and content analysis.
AI tools: llama3-70b-8192

Key findings

The chatbot supported information seeking once an action plan was established, but it proved counterproductive and distracting during initial exploratory phases.
Constant fact-checking induced verification fatigue, as unconstrained chatbot responses averaged 207.68 words compared to 32.11 words per query, often requiring validation of superficial or inaccurate content.
Traditional cues like bullet points lost informational value in chatbot responses, leading the learner to rely primarily on prior domain knowledge to detect useful hints.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

This full research paper investigates the impact of generative AI (GenAI) on the learner experience, with a focus on how learners engage with and utilize the information it provides. In e-learning environments, learners often need to navigate a complex information space on their own. This challenge is further compounded in interdisciplinary fields like bioinformatics, due to the varied prior knowledge and backgrounds. In this paper, we studied how GenAI influences information search in bioinformatics research: (1) How do interactions with a GenAI chatbot influence learner orienteering behaviors?; and (2) How do learners identify information scent in GenAI chatbot responses? We adopted an autoethnographic approach to investigate these questions. GenAI was found to support orienteering once a learning plan was established, but it was counterproductive prior to that. Moreover, traditionally value-rich information sources such as bullet points and related terms proved less effective when applied to GenAI responses. Information scents were primarily recognized through the presence or absence of prior knowledge of the domain. These findings suggest that GenAI should be adopted into e-learning environments with caution, particularly in interdisciplinary learning contexts.