CRII: CHS: Recommender Systems for Self-Actualization

每天，我们都面临着大量的决定，需要我们从看似无穷无尽的选择中做出选择。推荐系统应该帮助我们处理这个艰巨的任务，但一些学者声称，这些系统反而把我们放在一个“过滤气泡”中，严重限制了我们的观点。该项目研究了推荐系统研究的一个新方向，其主要目标是支持用户开发，探索和理解他们独特的个人偏好。该项目将开发一种新型的推荐系统：自我实现推荐系统（RSSA），它将支持对我们的生活产生深远影响的决定（例如，选择教育或工作），我们不想只采取最简单的选择，而是要发展自己成为独特的个体，具有强烈的决心，我们选择了正确的道路。与大多数现有的推荐系统研究相反，该项目仔细考虑了消费者选择过程的心理学，并开发了新类型的建议，以新颖的方式支持这些过程（RSSA功能）。PI的团队将开发一个新的推荐系统，该系统将能够显示传统的Top-N推荐列表，以及每个新的RSSA功能。然后，该团队将在在线用户实验中测试每个RSSA功能相对于传统Top-N推荐的好处。这一好处将通过参与者对系统的主观评价和他们的使用行为日志来衡量。

Every day, we are confronted with an abundance of decisions that require us to choose from a seemingly endless number of choice options. Recommender systems are supposed to help us deal with this formidable task, but some scholars claim that these systems instead put us inside a "Filter Bubble" that severely limits our perspectives. This project investigates a new direction for recommender systems research with the main goal of supporting users in developing, exploring, and understanding their unique personal preferences. The project will develop a new type of recommender system: a Recommender System for Self-Actualization (RSSA), which will support decisions that have a resounding influence on our life (e.g., choosing an education or a job) where we do not want to just take the easiest option, but rather to develop ourselves into unique individuals with a strong sense of determination that we have chosen the right path.In contrast to most existing recommender systems research, this project carefully considers the psychology of consumer choice processes and develops new types of recommendations to support these processes in novel ways (the RSSA features). The PI's team will develop a new recommender system outfitted with the capability to display a traditional Top-N recommendation list, plus each new RSSA feature. The team will then test the benefit of each RSSA feature against traditional Top-N recommendations in an online user experiment. This benefit will be measured by participants' subjective evaluation of the system and their usage behavior logs.