Xiudan Yang

Selection bias can cause recommendation systems to over-rely on users’ historical behavior and ignore potential interests, thus reducing the diversity and accuracy of recommendations. Our research on selection bias reveals that the existing literature often overlooks the impact of sentiment factors on selection bias. In recommendation tasks, sentiment bias—stemming from users’ sentiment reactions—can lead to the suggestion of low-quality products to important users and unfair recommendations of niche items (targeted at specific markets or purposes). Addressing sentiment bias and enhancing recommendations for key users could help balance research on selection bias. Sentiment bias is embedded in user ratings and reviews. To mitigate this bias, it is essential to analyze user ratings and comments to uncover genuine sentiments. To this end, we have developed a sentiment analysis module aimed at eliminating discrepancies between reviews and ratings, providing accurate sentiment scores, extracting users’ true opinions, and reducing sentiment bias. Additionally, we have designed a combinatorial function that adapts to three distinct scenarios for bias correction. Moreover, we introduce the concept of dynamic debiasing, where the modeling time is not fixed but varies over time. On this basis, we propose a dynamic selection debiased recommendation method based on sentiment analysis. This paper demonstrates how the three approaches—sentiment analysis for data sparsity, combinatorial functions for dataset optimization, and time-dynamic modeling with inverse propensity weighting—can effectively mitigate selection bias. Our experiments with multiple real-world datasets show that our model can significantly enhance recommendation performance.

Debiased recommendation has received significant attention from the academic community in recent years. Currently, our research on selection bias indicates that the existing literature ignores the effect of sentiment factors on selection bias. In the recommendation task, the existence of sentiment bias due to sentiment factors may lead to the recommendation of low-quality products to important users and unfair recommendation to niche(products designed for specific target markets and purposes) items. Eliminating sentiment bias and improving the quality of recommendations to important users can help balance research on selection bias. Sentiment bias is hidden in user ratings and reviews. Consequently, an effective approach to mitigate this bias is to analyze user ratings and comments in order to ascertain their genuine opinions. We have developed a sentiment analysis module with the objective of eliminating the bias between reviews and ratings, providing accurate sentiment ratings, mining users' real sentiment opinions, and eliminating the sentiment bias. Currently, a combinatorial function is constructed that performs the corresponding computations based on three different scenarios. Furthermore, the concept of dynamic debiasing is introduced, where the modeling time is dynamic. A selection debiasing recommendation method based on time-dynamic scenarios is also proposed. This paper demonstrates how the three aforementioned approaches can effectively mitigate selection bias by addressing data sparsity (sentiment analysis), optimizing data at the level of the data set (combinatorial functions), and considering dynamic scenarios and applying inverse propensity weighting methods (time-dynamic modeling). Our experiments on several real datasets demonstrate that our model can effectively improve the performance of recommendations.

Event causality identification is an upstream operation for many tasks, including knowledge graphs and intelligent question-and-answer systems. The latest models introduce external knowledge and then use deep learning for causality prediction. However, event causality recognition still faces problems such as data imbalance and insufficient event content richness. Additionally, previous frameworks have utilized a single model, but these frequently produce unsatisfactory outcomes such as lower precision rates and lower recall rates. We propose the concept of ensemble learning, which combines multiple models to achieve frameworks that perform as well as or better than the latest models. This framework combines the advantages of Mamba, a temporal convolutional network, and graph computation to identify event causality more effectively and accurately. After comparing our framework to standard datasets, our F1-scores (measures of model accuracy) are essentially the same as those of the state-of-the-art (SOTA) methods on one dataset.