Reducing Cross-Topic Political Homogenization in Content-Based News Recommendation
Reducing Cross-Topic Political Homogenization in Content-Based News Recommendation
复制标题
DOI：
10.1145/3523227.3546782
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
K. Shivaram;Ping Liu;Matthew Shapiro;M. Bilgic;A. Culotta
中科院分区：
文献类型：
--
作者：
K. Shivaram;Ping Liu;Matthew Shapiro;M. Bilgic;A. Culotta
基于内容的新闻推荐器学习与用户参与度相关的单词并相应地推荐文章。对于按主题具有不同政治偏好的用户来说，这可能会出现问题 - 例如，在一个主题上喜欢保守派文章但在另一主题上喜欢自由派文章的用户。在这种情况下，推荐者可以通过推荐对两个主题具有相同政治倾向的文章来产生同质化效果，特别是如果两个主题都具有“极右”或“激进左”等显着的政治两极分化术语。在本文中，我们提出了基于注意力的神经网络模型，通过增加对特定主题单词的注意力，同时减少对极化的、主题通用术语的注意力，来减少这种同质化效应。我们发现所提出的方法可以为具有不同偏好的模拟用户提供更准确的推荐。
Content-based news recommenders learn words that correlate with user engagement and recommend articles accordingly. This can be problematic for users with diverse political preferences by topic — e.g., users that prefer conservative articles on one topic but liberal articles on another. In such instances, recommenders can have a homogenizing effect by recommending articles with the same political lean on both topics, particularly if both topics share salient, politically polarized terms like “far right” or “radical left.” In this paper, we propose attention-based neural network models to reduce this homogenization effect by increasing attention on words that are topic specific while decreasing attention on polarized, topic-general terms. We find that the proposed approach results in more accurate recommendations for simulated users with such diverse preferences.