Abstract
Two computational studies provide different sentiment analyses for text segments (e.g., “fearful” passages) and figures (e.g., “Voldemort”) from the Harry Potter books (Rowling, 1997, 1998, 1999, 2000, 2003, 2005, 2007) based on a novel simple tool called SentiArt. The tool uses vector space models together with theory-guided, empirically validated label lists to compute the valence of each word in a text by locating its position in a 2d emotion potential space spanned by the words of the vector space model. After testing the tool's accuracy with empirical data from a neurocognitive poetics study, it was applied to compute emotional figure and personality profiles (inspired by the so-called “big five” personality theory) for main characters from the book series. The results of comparative analyses using different machine-learning classifiers (e.g., AdaBoost, Neural Net) show that SentiArt performs very well in predicting the emotion potential of text passages. It also produces plausible predictions regarding the emotional and personality profile of fiction characters which are correctly identified on the basis of eight character features, and it achieves a good cross-validation accuracy in classifying 100 figures into “good” vs. “bad” ones. The results are discussed with regard to potential applications of SentiArt in digital literary, applied reading and neurocognitive poetics studies such as the quantification of the hybrid hero potential of figures.
Highlights
Computational analysis and modeling of narratives or poetry still present a wealth of challenges for research in digital literary studies, computational linguistics, machine learning, or neurocognitive poetics (e.g., Nalisnick and Baird, 2013; Ganascia, 2015; Jacobs, 2015a, 2018b)
The point is that within the confines of the present special materials tested in several neurocognitive poetics studies (Hsu et al, 2015a,b,c), SentiArt’s performance can be considered as competitive
Applying the empirically validated techniques developed for sentiment analysis (SA) of texts to fiction characters produced some interesting results with plausible face validity, highaccuracy identification of 100 figures and a decent classification accuracy regarding “goodness” of character data for those figures sampled from the internet
Summary
Computational analysis and modeling of narratives or poetry still present a wealth of challenges for research in digital literary studies, computational linguistics, machine learning, or neurocognitive poetics (e.g., Nalisnick and Baird, 2013; Ganascia, 2015; Jacobs, 2015a, 2018b). While there is considerable progress in SA in the last 20 years (e.g., Liu, 2015), when it comes to poetic texts such as Shakespeare sonnets (Simonton, 1989; Jacobs et al, 2017) new challenges like the prediction of aesthetic emotions via SA tools must be tackled. In order to tackle this issue I use a vector space model (VSM)-based SA tool that has proven useful for computing the emotion potential of poems and of excerpts from Rowling’s (1997, 1998, 1999, 2000, 2003, 2005, 2007) Harry Potter book series (Jacobs, 2018a,b)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
