Beyond Recommendation Accuracy: A Human-Like Recommender System

• Main Author: Al-slaity, Ala'a Nasir
• Other Authors: Tran, Thomas
• Format: Others
• Language: en
• Published: Université d'Ottawa / University of Ottawa 2021
• Subjects: Recommender Systems; Persuasive Technology; Persuasive Principles; User personality
• Online Access: http://hdl.handle.net/10393/41881; http://dx.doi.org/10.20381/ruor-26103

Since the emergence of Recommender Systems (RS), most of the research has focused on improving the capability of a recommender system to predict and provide an accurate recommendation. However, the literature has demonstrated increasing evidence that providing accurate recommendations is not sufficient to increase users’ acceptance of the provided recommendations. Hence, it is vital for a recommender system to focus not only on the accuracy of the provided recommendations but also on other factors that influence the acceptance of recommendations and the extent to which these recommendations are convincing or persuasive. Consequently, there becomes a need for new research paradigms to help improve the capabilities of recommender systems, which goes beyond the recommendation accuracy. One of the recently emerged research directions that consider this need fosters the idea of adopting human-related theories from the social sciences domain, such as persuasiveness of social communication. In this context, however, a challenging, non-trivial, and not fully explored issue that arises is: how to integrate human-related theories into a recommender system to be one of its intrinsic characteristics in order to improve its performance beyond its accuracy? This thesis aims to address the above issue from two angles: first, it investigates improving recommender systems by increasing users’ acceptance of the recommendations. To achieve this, the influence of persuasion principles on users of recommender systems is investigated. Then a reference architecture framework to adapt and integrate persuasion features as a substantial characteristic of recommender systems is proposed. The proposed framework, named Personalized Persuasive RS (PerPer), adopts concepts from the social sciences literature, namely personality traits and persuasion principles. In addition, PerPer adapts machine learning concepts, in particular, the Learning Automata, to support its learning capabilities. Second, the thesis discusses evaluating recommender systems beyond their accuracy. Particularly, it proposes two evaluation approaches that aim to evaluate recommender systems in a comprehensive way that goes beyond evaluating accuracy only. The first evaluation approach is called the Comprehensive Performance evaluation (ComPer). It adopts concepts from the human learning domain and provides a simple, thorough, and setting-independent evaluation approach for recommenders. The essence of ComPer is to consider a recommender system as a human being, and hence the former’s outcomes (i.e., recommendations) can be evaluated and validated in a way similar to how humans’ learning outcomes are evaluated. The second evaluation approach adopts goal-oriented modeling to provide an evaluation that does not only assess recommenders beyond their accuracy but also considers the multi-stakeholders of RSs. We demonstrate, empirically, and by user studies, the feasibility and usefulness of the proposed approaches. The contributions of the thesis are: (1) A characterization of recommender systems as systems supported with human traits and features, which goes beyond the conventional recommender systems known in the literature. (2) A user study that examines the impact of persuasive principles on users of recommender systems. (3) A Personalized Persuasive RS (PerPer) reference architecture framework to enrich recommender systems with persuasion capabilities that are personalized and adaptive for different users. (4) A mapping between human’s cognitive skills and the recommendation process. (5) The Comprehensive Performance evaluation (ComPer) framework to provide a comprehensive assessment of recommender systems considering multiple evaluation dimensions other than accuracy. And (6) a goal-oriented evaluation approach to assess the impact of multiple alternatives for recommendation approaches on the satisfaction of RSs stakeholders’ goals.