“Killing Me” Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 3613–3617 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 3613 “Killing Me” Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism Buru Chang† Inggeol Lee‡ Hyunjae Kim‡ Jaewoo Kang‡∗ Hyperconnect† Korea University‡ buru@hpcnt.com {ingulbull,hyunjae-kim,kangj}@korea.ac.kr Abstract Several machine learning-based spoiler detec- tion models have been proposed recently to protect users from spoilers on review websites. Although dependency relations between con- text words are important for detecting spoilers, current attention-based spoiler detection mod- els are insufficient for utilizing dependency re- lations. To address this problem, we propose a new spoiler detection model called SDGNN that is based on syntax-aware graph neural networks. In the experiments on two real- world benchmark datasets, we show that our SDGNN outperforms the existing spoiler de- tection models. 1 Introduction Spoilers on review websites, which reveal criti- cal details of the original works, can ruin an ap- preciation for the works. Review websites, such as Rotten Tomato, IMDb, and Metacritic, provide self-reporting systems that tag spoiler information to warn users of spoilers. However, since self- reporting systems depend solely on the active par- ticipation of users, they cannot handle the fast- growing volume of newly generated reviews. Dur- ing the past decade, several machine learning-based spoiler detection (SD) models have been proposed to solve the inefficiency of self-reporting systems. Guo and Ramakrishnan (2010) proposed an auto- matic SD model that measures the similarity be- tween reviews and synopses of movies. Support vector machine (SVM)-based SD models using handcrafted features have been proposed (Boyd- Graber et al., 2013; Jeon et al., 2016). Recently, attention-based SD models that utilize metadata of ∗Corresponding author. †This work was done while the author was affiliated with Korea University. Theresa killing Thomas plans on it killing me is but I think I will forgive Label O X Predicted O O pcomp dobj nsubj dobj aux Figure 1: Attention-based models focused on the word “killing” because the word is frequently used in spoiler sentences, which results in incorrect predictions. review documents achieve state-of-the-art perfor- mance on the SD task (Chang et al., 2018; Wan et al., 2019). However, the attention-based SD models have a lack of using dependency relations between con- text words. Dependency relations are useful for capturing the semantics of given sentences and de- tecting spoilers. As shown in Figure 1, although the phrase “killing me” is not a spoiler because the phrase is a metaphor, the attention-based SD models often focus on the word “killing” and clas- sify sentences that contain the phrase “killing me” as spoilers. By providing the information that the word “me” is used as the direct object of the verb “killing,” SD models can understand that the phrase is a metaphor. In this paper, we propose SDGNN, which is a new Spoiler Detection model based on syntax- aware Graph Neural Networks (GNNs) (Marcheg- giani and Titov, 2017) for leveraging dependency relations between …

Content truncated to 500 words