• Organisation

We are interested in the textual features that correlate with reported impact by readers of novels. We operationalize impact measurement through a rule-based reading impact model and apply it to 634,614 reader reviews mined from seven review platforms. We compute co-occurrence of impact-related terms and their keyness for genres represented in the corpus. The corpus consists of the full text of 18,885 books from which we derived topic models. The topics we find correlate strongly with genre, and we get strong indicators for what key impact terms are connected to which genre. These key impact terms gives us a first evidence-based insight into genre-related readers’ motivations.

This paper has been submitted to the conference track of JCLS. It has been peer reviewed and accepted for presentation and discussion at the 3rd Annual Conference of Computational Literary Studies at Vienna, Austria, in June 2024.