Year: 2026
Type: conference-paper
Abstract: Our team was interested in content classification and labeling from toxicity detection of gaming chat logs in online gaming communities.We joined the shared task on Understanding Toxic Behavioral Intent in Gaming Chat Logs@EEUCA with ACL 2026.In this task, our goal is to assign a content classification label to player's utterance (e.g., Hate and Harassment, Threats, Non-toxic).The objective is to develop systems that can classify the intent of a player's utterance.The dataset for this task will have five labels: Non-toxic (0), Insults and Flaming (1), Other Offensive Texts (2), Hate and Harassment (3), Threats (4) and Extremism (5).The performance will be ranked by F1-score (Macro).The task utilizes 53,000 game chat utterances from World of Tanks.Our group used a supervised learning method on multiple pre-trained models and finetuning Qwen2 LLMs.The best result on the test set for shared task were Macro F1 score of 0.5776, Accuracy 0.9075, Precision (Macro) 0.6847, and Recall (Macro) 0.5343 from finetuning qwen2 7B LLM method, ranking 8th among all teams.The complete code of this entire project can be found at our GitHub address 1 .
Authors: Kongqiang Wang, Peng Zhang, Quingli Tan
Institution: Yunnan University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Yunnan University
OpenAlex ID: W7166801212