Real-time Prediction of Dota 2 Match Outcomes using In-game Chat Logs
Open Access
- 7 November 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Vol. 21 (1) , 186-195
Abstract
This paper investigates the application of supervised learning for the purpose of match outcome prediction from Dota 2 in game chat logs. We analyze a dataset of 50,000 ranked matches, evaluating the predictive power of communication data alone and in combination with game events. Using LSTM and DistilBERT architectures, alongside a logistic regression baseline, we demonstrate that chat logs alone enable accurate prediction (up to 81.4% accuracy), while incorporating game events substantially improves performance (up to 98.4% accuracy). Our temporal analysis reveals that prediction reliability increases significantly during the mid-game phase (15-30 minutes), with models exhibiting different strengths - LSTM achieves higher accuracy while DistilBERT demonstrates greater prediction confidence. This study contributes to esports analytics by establishing chat logs as a viable predictive data source.Keywords
This publication has 5 references indexed in Scilit:
- A BERT Framework to Sentiment Analysis of TweetsSensors, 2023
- Towards Detecting Contextual Real-Time Toxicity for In-Game Chat2023
- AI-enabled prediction of video game player performance using the data from heterogeneous sensorsMultimedia Tools and Applications, 2022
- Win Prediction in Multiplayer Esports: Live Professional Match PredictionIEEE Transactions on Games, 2019
- Prediction of DOTA 2 Match Result by Using Analytical Hierarchy Process MethodInternational Journal of Engineering and Emerging Technology, 2017