⽤⼾感知外的回饋揭露意願因素

Factors influencing feedback disclosure intention beyond users’ perception

楊昇祐(Yang Sheng-You)

指導教授 ： 林怡伶

國立政治大學/商學院/資訊管理學系/碩士(2021年)

https://doi.org/10.6814/NCCU202101309

摘要

如今，推薦系統被普遍用於解決各種網站和APP中資訊過載的問題。且許多研究都集中在如何提高推薦準確性。「回饋」是提高推薦準確性和滿足用戶需求的方法之一。然而，用戶往往不願意主動提供回饋。以往的研究表明，回饋資訊揭露的意願受到感知利益、風險評估和應對評估等因素的影響。儘管如此，這些因素只考慮到了用戶本身。而「用戶與環境的關係（情境）」和「用戶與產品的關係（產品參與）」並沒有被考量過。本研究以餐廳推薦系統為例，旨在討論用戶本身外其他影響回饋揭露意願的因素。在實驗的第一部分，透過問卷對104名參與者進行了前測；在第二部分，透過餐廳推薦APP對67名參與者進行了實地研究。結果表明，活動情境、時間和參與度，是要求用戶提供回饋時，需要考慮的基本因素。

關鍵字

推薦系統 ； 餐廳推薦 ； 情境 ； 產品參與 ； 回饋 ； 揭露意願

並列摘要

Recommender systems are commonly used to solve information overload problems in various websites and APPs nowadays. Many studies focus on the issue of increasing recommendation accuracy. “Feedback” is one of the methods to enhance recommendation accuracy and fulfill users’ needs. However, users are often not willing to provide feedback actively. Previous study demonstrates that feedback information disclosure intention is influenced by factors from the perspectives of perceived benefits, risk appraisal, and coping appraisal. Nonetheless, these factors only take users themselves into account. The “user-environment relationship (context)” and “user-product relationship (product involvement)” have not been considered. This study takes the restaurant recommender system as an example and aims to discuss the factors that influencing feedback disclosure intention. A pretest study was conducted with 104 participants by questionnaire in the experiment first section and a field study was conducted with 67 participants by restaurant recommendation APP in the second section. The results indicating that activity context, timing, and involvement are essential factors to be considered when requesting the user to provide feedback.

並列關鍵字

Recommender system ； Restaurant recommendation ； Context ； Product involvement ； Feedback ； Disclosure intention

參考文獻

Adomavicius, G., & Tuzhilin, A. (2011). Context-aware recommender systems. In Recommender Systems Handbook.

Aljukhadar, M., Senecal, S., & Daoust, C. E. (2012). Using recommendation agents to cope with information overload. International Journal of Electronic Commerce.

Amatriain, X., Pujol, J. M., Tintarev, N., & Oliver, N. (2009). Rate it again: Increasing recommendation accuracy by user re-rating. RecSys’09 - Proceedings of the 3rd ACM Conference on Recommender Systems.

Baum, D., & Spann, M. (2014). The interplay between online consumer reviews and recommender systems: An experimental analysis. In International Journal of Electronic Commerce (Vol. 19).

Betzalel, N. D., Shapira, B., & Rokach, L. (2015). “Please, not now!” A model for timing recommendations. RecSys 2015 - Proceedings of the 9th ACM Conference on Recommender Systems, 297–300.