Systematic improvement of user engagement with academic titles using computational linguistics

摘要: This paper describes a novel approach to systematically improve information interactions based solely on its wording. Following an interdisciplinary literature review, we recognized three key attributes of words that drive user engagement: (1) Novelty (2) Familiarity (3) Emotionality. Based these attributes, developed model given content using computational linguistics, natural language processing (NLP) and text analysis (word frequency, sentiment lexical substitution). We conducted pilot study (n=216) in which the was used formalize evaluation optimization academic titles. A between-group design (A/B testing) compare responses original modified (treatment) Data collected for selection (User Engagement Scale). The results suggest engagement with digital is fostered by, perhaps dependent upon, wording being used. They also provide empirical support engaging can be evaluated produced. preliminary show titles had significantly higher scores use (selection evaluation). propose linguistics useful optimizing interactions. empirically insights inform development strategies, thereby improving success interactions.elop more sophisticated interaction measures.