用神经符号AI实现新闻推荐多维度多样性，提升用户与社会体验
Towards Multi-Aspect Diversification of News Recommendations Using Neuro-Symbolic AI for Individual and Societal Benefit
- 融合知识图谱与规则学习，实现观点、序列等四类多样性推荐
- 通过用户研究评估行为与感知体验，验证多样性提升效果
- 兼顾个体获得感与社会减极化，推动更健康的信息生态
新闻推荐复杂且多样性至关重要。现有研究多聚焦单一维度，如观点多样性。本文提出四种推荐模式下的多方面多样性框架，指出列表、序列、摘要和交互多样化的具体挑战。我们结合符号与非符号人工智能，利用知识图谱与规则学习构建模型，并计划通过用户研究同时捕捉行为数据与主观体验。该研究旨在平衡新闻消费，带来个体层面的惊喜感提升与社会层面的极化缓解等积极影响。
原文摘要 · Abstract (English)
News recommendations are complex, with diversity playing a vital role. So far, existing literature predominantly focuses on specific aspects of news diversity, such as viewpoints. In this paper, we introduce multi-aspect diversification in four distinct recommendation modes and outline the nuanced challenges in diversifying lists, sequences, summaries, and interactions. Our proposed research direction combines symbolic and subsymbolic artificial intelligence, leveraging both knowledge graphs and rule learning. We plan to evaluate our models using user studies to not only capture behavior but also their perceived experience. Our vision to balance news consumption points to other positive effects for users (e.g., increased serendipity) and society (e.g., decreased polarization).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。