Using Cohesion-Based and Sentiment-Based Attributes to Classify Spoilers in Movie Reviews
Issued Date
2022-01-01
Resource Type
Scopus ID
2-s2.0-85145350908
Journal Title
2022 5th International Conference on Computer and Informatics Engineering, IC2IE 2022
Start Page
80
End Page
84
Rights Holder(s)
SCOPUS
Bibliographic Citation
2022 5th International Conference on Computer and Informatics Engineering, IC2IE 2022 (2022) , 80-84
Suggested Citation
Marukatat R. Using Cohesion-Based and Sentiment-Based Attributes to Classify Spoilers in Movie Reviews. 2022 5th International Conference on Computer and Informatics Engineering, IC2IE 2022 (2022) , 80-84. 84. doi:10.1109/IC2IE56416.2022.9970137 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/84325
Title
Using Cohesion-Based and Sentiment-Based Attributes to Classify Spoilers in Movie Reviews
Author(s)
Author's Affiliation
Other Contributor(s)
Abstract
Spoiler reviews have different narrative patterns from non-spoiler reviews. Their narrative is more precise about what happened in the movies, while that of non-spoiler reviews is more obscure due to the omission of specific details. Our research extracted 108 cohesion-based and 6 sentiment-based attributes from movie reviews, which captured these patterns. The classification was done using Naive Bayes and a support vector machine (SVM) with a linear kernel. SVM achieved the best performance of 78% accuracy and 0.78 F -measure of class spoiler. Most contributing attributes were also determined from the weight vector given by the SVM. They supported our initial observation about the differences in narrative patterns between spoilers and non-spoilers.