An artificial intelligence assistant to reader response theory: Pioneering novel analysis in the digital age

Abstract

This study investigates the impact of an artificial intelligence (AI) assistant on reader response theory in novel analysis using a mixed-methods approach. It examines how AI-generated real-time feedback, powered by advanced machine learning and natural language processing, enhances interpretive possibilities beyond conventional methods, aligning with reader response theory’s emphasis on reader-text interaction. The AI assistant, designed with Real-Time Theme Identification, Character Relationship Mapping, Symbolism Detection, and Interactive Literary Simulation, supports nuanced interpretations, uncovers underlying patterns, and fosters deeper engagement with literary texts. Participants ( n = 100), aged 15–18 years, were divided into an experimental group ( n = 50), which used the AI assistant for novel analysis, and a control group ( n = 50), which relied on traditional literary analysis methods. Quantitative data were collected through pre- and post-study assessments of participants’ interpretive skills, measured on a 100-point scale, while qualitative insights were gathered via in-depth interviews and focus groups. The AI’s effectiveness in interpretive skills and comprehension was evaluated by comparing outcomes between groups. The results show that the experimental group markedly outperformed the control group, with a mean increase in interpretation scores from 70.5 (SD = 6.1) to 85.2 (SD = 5.8; t (49) = 5.23, p < .001), reflecting a 20.8% improvement in identifying textual connections and a 15% increase in offering diverse perspectives. In contrast, the control group’s scores rose modestly from 69.8 (SD = 6.3) to 75.1 (SD = 6.2; t (49) = 2.14, p < .05), showing only a 7.6% improvement in textual connections and a 5% increase in diverse perspectives. Qualitative findings indicated improved comprehension, critical thinking, motivation, and emotional engagement, with 80% of participants reporting increased analytical confidence due to the AI assistant. These results suggest that AI integration advances reader response theory, improves interpretation, and enhances accessibility for diverse students in digital literary education.