Subjects: Psychology >> Applied Psychology submitted time 2019-01-22
Abstract: Players preferences for different types of games are influenced by their own characteristics. The number of players determines that the mode of single player game is more independent, while the mode of online game mode is more collaborative. Given that individualism individuals tend to emphasize independence, collectivism individuals emphasize collaboration. We hypothesized that players’ individualism-collectivism tendency may affect their preference for single player game or online game. This study used Weibo user’s data to explore whether there was a difference in individualism-collectivism words expressions between single player game players and online game players. Then we used these features to predict players single player or online game preferences. The result showed that single player game players expressed more individualism words in Weibo, while online game players expressed more collectivism words. Using machine learning method, individualism-collectivism words expressions could predict players type, but accuracy of the model was low. This study provided preliminary evidence for using Weibo data to identify users preference for games, thus had certain application value.
Peer Review Status:Awaiting Review
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-07-23 Cooperative journals: 《计算机应用研究》
Abstract: As the limitations of the single classifier on traffic accident severity, an ensemble approach is proposed for improving the prediction performance. Using CNNs to extract the features from the spatial dimension, getting an ensemble approach with XGBoost and CNN by stacking (multi-level boosting algorithm) . The predicting precision of the approach is 91.51% on the validation set. In comparison with the single classification model, the result of the experiment shows a better performance. For providing useful information for reducing the number of traffic accidents and downgrading the severity of traffic accident, the paper gives out a correlation analysis by sorting the features based on the predictions.