Sorcerer’s Apprentice? Exploring an AI-Driven Tool to Analyze Academic Texts

The exponential growth of scholarly publications in recent years has presented a daunting challenge for researchers to keep track of relevant articles within their research field. To address this issue, we examined the capabilities of InfraNodus, an AI-Powered text network analysis platform. InfraNodus promises to provide insights into any discourse, uncover blind spots, and enhance a scholar’s perspective by representing text as a network graph with relevant topical clusters and their relations. To explore the tool’s effectiveness in analyzing scholarly articles, we embarked on an AI-assisted review of research papers, initially using a set of 15 abstracts and 15 full papers. It transpired that InfraNodus could indeed create plausible topical clusters and apparently meaningful patterns from abstracts, but its generated questions and summaries lacked both relevance to and coherence with the articles’ contents, sometimes misconstruing concepts and constructs. A deeper understanding of how the AI operates within the tool would benefit researchers seeking to optimize their literature review processes, as well as to understand the grave risks AI-generated plausibility and appearance present to academic ethics and intellectual integrity.