Editable User Profiles for Controllable Text Recommendations

Editable User Profiles for Controllable Text Recommendations
复制标题

用于可控文本推荐的可编辑用户配置文件

DOI:
10.1145/3539618
复制
发表时间:
2023
期刊:
ACM
影响因子:
--
通讯作者:
Zamani, Hamed
Zamani, Hamed
中科院分区:
--
文献类型:
--
作者:
Mysore, Sheshera;Jasim, Mahmood;McCallum, Andrew;Zamani, Hamed

文献摘要

参考文献

被引文献

相似文献

做出高质量推荐的方法通常依赖于从交互数据中学习潜在表示。这些方法虽然性能良好,但没有为用户提供现成的机制来控制他们收到的推荐。我们的工作解决了这个问题,提出了LACE,一个新的概念值瓶颈模型可控的文本推荐。LACE通过检索给定的用户交互文档,用一组简洁的人类可读概念来表示每个用户,并基于用户文档学习概念的个性化表示。然后利用基于概念的用户简档来进行推荐。我们的模型的设计提供了控制的建议,通过一些直观的互动与透明的用户配置文件。我们首先建立了从LACE中获得的建议的质量,在离线评估中,在热启动,冷启动和零拍摄设置中,跨越六个数据集的三个推荐任务。接下来,我们验证了LACE的可控性下模拟用户交互。最后,我们实现了LACE在一个交互式可控推荐系统,并进行了用户研究,以证明用户能够提高他们收到的建议,通过与可编辑的用户配置文件的交互质量。
Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive. Our work tackles this problem by proposing LACE, a novel concept value bottleneck model for controllable text recommendations. LACE represents each user with a succinct set of human-readable concepts through retrieval given user-interacted documents and learns personalized representations of the concepts based on user documents. This concept based user profile is then leveraged to make recommendations. The design of our model affords control over the recommendations through a number of intuitive interactions with a transparent user profile. We first establish the quality of recommendations obtained from LACE in an offline evaluation on three recommendation tasks spanning six datasets in warm-start, cold-start, and zero-shot setups. Next, we validate the controllability of LACE under simulated user interactions. Finally, we implement LACE in an interactive controllable recommender system and conduct a user study to demonstrate that users are able to improve the quality of recommendations they receive through interactions with an editable user profile.
推荐系统中的用户控制:概述和交互挑战
DOI: --
发表时间: 2016
期刊: International Conference on Electronic Commerce and Web Technologies
影响因子: --
作者:
D. Jannach;Sidra Naveed;Michael Jugovac
通讯作者: Michael Jugovac
DOI: 10.1145/3460231.3474276
发表时间: 2021-09
期刊: Proceedings of the 15th ACM Conference on Recommender Systems
影响因子: --
作者:
Longqi Yang;Tobias Schnabel;Paul N. Bennett;S. Dumais
通讯作者: Longqi Yang;Tobias Schnabel;Paul N. Bennett;S. Dumais
DOI: 10.1145/3336191.3371818
发表时间: 2020-01
期刊: Proceedings of the 13th International Conference on Web Search and Data Mining
影响因子: --
作者:
Hamed Zamani
通讯作者: Hamed Zamani
DOI: --
发表时间: 2018-06
期刊: J. Mach. Learn. Res.
影响因子: --
作者:
Ivan Stelmakh;Nihar B. Shah;Aarti Singh
通讯作者: Ivan Stelmakh;Nihar B. Shah;Aarti Singh
通过用户控制的推荐将学生与研究顾问联系起来
DOI: --
发表时间: 2021
期刊: ACM Conference on Recommender Systems
影响因子: --
作者:
Behnam Rahdari;Peter Brusilovsky;Alireza Javadian Sabet
通讯作者: Alireza Javadian Sabet