A Knowledge Graph Approach for Analyzing Player Social Media Reviews
DOI:
https://doi.org/10.52731/liir.v006.413Keywords:
Game reviews, Graph neural networks, Knowledge graph, Sentiment analysisAbstract
In recent years, as the gaming industry has developed, both the number of games and players have continuously increased. However, in recent years, numerous conflicts have arisen between game developers and players, leading to significant consequences for both parties. These incidents stem from a lack of effective communication between the two sides. Meanwhile, player communities have amassed a wealth of authentic reviews posted by actual players, reflecting their most genuine opinions about the games. To address this issue, the present study conducts sentiment analysis on reviews from player communities and proposes the use of graph neural networks (GNN) along with a knowledge graph constructed from gaming wikis to uncover the deep-seated reasons behind the various emotions expressed by players. Additionally, a pre-trained large model is employed to better understand player feedback, thereby enabling game developers to establish more effective communication with their player base.
References
Kong Shao-hua. Research on user information behavior massively multiplayer online game virtual community—an example of netease’s massively multiplayer online game fantasy westward journey. Information Sciences, 2013.
Fujio Toriumi, Takeshi Sakaki, and Mitsuo Yoshida. Social emotions under the spread of covid-19 using social media. The Japanese Society for Artificial Intelli-gence, 35(4):F-K45 1–7, 2020.
Mehrimah Amirpour and Reza Azmi. Prfashion24: A dataset for sentiment analysis of fashion products reviews in persian, 05 2024.
Xiaoyu Zhang, Yishan Li, Jiayin Wang, Bowen Sun, Weizhi Ma, Peijie Sun, and Min Zhang. Large language models as evaluators for recommendation explanations. In Proceedings of the 18th ACM Conference on Recommender Systems, RecSys ’24, page 33–42, New York, NY, USA, 2024. Association for Computing Machinery.
Junichiro Niimi. Dynamic sentiment analysis with local large language models using majority voting: A study on factors affecting restaurant evaluation. 07 2024.
Jiashuo Sun, Chengjin Xu, Luminyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Heung-Yeung Shum, and Jian Guo. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph, 07 2023.
Claudiu Creanga and Liviu P. Dinu. ISDS-NLP at SemEval-2024 task 10: Trans-former based neural networks for emotion recognition in conversations. In Atul Kr. Ojha, A. Scza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, and Aiala Rosá, editors, Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 649–654, Mexico City, Mexico, June 2024. Association for Computational Linguistics.
