Emotion-Based Literature Book Classification Using Online Reviews

Reading is not only a recreational activity; it also shapes the emotional and cognitive competences of the reader. In this paper, we present a method and tools for the analysis of emotions extracted from online reviews of literature books. We implement a scraper to create a new experimental dataset of reviews gathered from Goodreads, a website dedicated to readers that contains a large database of books and readers' reviews. We propose a system which extracts the emotions from the reviews and associates them with the reviewed book. Afterwards, this information can be used to find similarities between the books based on readers' impressions. Lastly, we show the experimental setup, consisting of the user interface developed for the proposed system, together with the experimental results.

Automated summary

This paper presents a method and tools for extracting emotions from online reviews of literature books, as well as a system that uses this information to find similarities between books. The experimental results demonstrate the effectiveness of the proposed system.