Zobrazeno 1 - 10
of 296
pro vyhledávání: '"Konstan, Joseph A"'
An increasingly important aspect of designing recommender systems involves considering how recommendations will influence consumer choices. This paper addresses this issue by introducing a method for collecting user beliefs about un-experienced items
Externí odkaz:
http://arxiv.org/abs/2405.11053
This paper explores the effectiveness of using large language models (LLMs) for personalized movie recommendations from users' perspectives in an online field experiment. Our study involves a combination of between-subject prompt and historic consump
Externí odkaz:
http://arxiv.org/abs/2404.19093
Autor:
Sun, Ruixuan, Wu, Xinyi, Akella, Avinash, Kong, Ruoyan, Knijnenburg, Bart, Konstan, Joseph A.
In the past decade, deep learning (DL) models have gained prominence for their exceptional accuracy on benchmark datasets in recommender systems (RecSys). However, their evaluation has primarily relied on offline metrics, overlooking direct user perc
Externí odkaz:
http://arxiv.org/abs/2401.11632
E-mail ``Messages From the President'' to university students, staff, and faculty have long been used to keep campus communities aware of the latest policies, events, and news. But during the COVID-19 pandemic, as universities quickly closed faciliti
Externí odkaz:
http://arxiv.org/abs/2401.11135
Recommender systems often struggle to strike a balance between matching users' tastes and providing unexpected recommendations. When recommendations are too narrow and fail to cover the full range of users' preferences, the system is perceived as use
Externí odkaz:
http://arxiv.org/abs/2309.13296
The COVID-19 pandemic has forced many employees to work from home. Organizational bulk emails now play a critical role to reach employees with central information in this work-from-home environment. However, we know from our own recent work that orga
Externí odkaz:
http://arxiv.org/abs/2308.05085
Autor:
Chancellor, Stevie1 (AUTHOR) steviec@umn.edu, Konstan, Joseph A.1 (AUTHOR) konstan@umn.edu, Terveen, Loren1 (AUTHOR) terveen@umn.edu, Yarosh, Svetlana2 (AUTHOR) lana@umn.edu
Publikováno v:
Communications of the ACM. Jun2024, Vol. 67 Issue 6, p35-38. 4p.
In this study, we partition users by rating disposition - looking first at their percentage of negative ratings, and then at the general use of the rating scale. We hypothesize that users with different rating dispositions may use the recommender sys
Externí odkaz:
http://arxiv.org/abs/2306.11279
Autor:
Kong, Ruoyan, Sun, Ruixuan, Zhang, Charles Chuankai, Chen, Chen, Patri, Sneha, Gajjela, Gayathri, Konstan, Joseph A.
Publikováno v:
In Proceedings of the 2023 Symposium on Eye Tracking Research and Applications, ETRA 23, New York, NY, USA, 2023
A single digital newsletter usually contains many messages (regions). Users' reading time spent on, and read level (skip/skim/read-in-detail) of each message is important for platforms to understand their users' interests, personalize their contents,
Externí odkaz:
http://arxiv.org/abs/2306.07455
Autor:
Kong, Ruoyan, Zhang, Chuankai, Sun, Ruixuan, Chhabra, Vishnu, Nadimpalli, Tanushsrisai, Konstan, Joseph A.
Bulk email is often used in organizations to communicate ``important-to-organization'' messages such as policy changes, organizational plans, and administrative updates. However, normal employees may prefer messages more relevant to their jobs or int
Externí odkaz:
http://arxiv.org/abs/2302.11156