Answers are grounded in this paper and cite their sources.
Evaluating popular educational chatbots (EC) shows that existing EC impacts users' ability to synthesize and take ownership of their work. This study designs and evaluates a research-guided chatbot intended to support novice researchers by promoting structured cognition, idea ownership, and emotional engagement during early research planning. A total of 165 graduate students completed the chatbot activity; 95 provided valid questionnaire responses, and 78 submitted analyzable open-ended reflections. Qualitative feedback was analyzed using exploratory sentiment and emotion detection to identify overall affective tendencies rather than psychometric constructs. The findings show that "interesting" and "enjoyable" were frequent words used in user feedback. Sentiment analysis is reported as exploratory, aiming to identify general affective tendencies rather than to support inferential or scale-based claims. Respondents have confidence in the chatbot's reliability and accuracy. Two themes were identified in the thematic analysis: attitudes and improvements to future research-guided chatbots, emphasizing simplicity. Findings indicate that guided interaction may indirectly enhance and support research emotions by reducing uncertainty, supporting autonomy, and externalizing the structure of the research process. Rather than claiming superiority over generative AI systems, the study proposes a complementary design paradigm emphasizing guidance over generation.
No takes yet. Share an insight, caveat, or question.
Vadivel et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: