Ontological user profiling in recommender systems

By Stuart E. Middleton, Nigel R. Shadbolt, David De Roure. TOIS, 2004

857 citations recorded by the source corpus.

We explore a novel ontological approach to user profiling within recommender systems, working on the problem of recommending on-line academic research papers. Our two experimental systems, Quickstep and Foxtrot, create user profiles from unobtrusively monitored behaviour and relevance feedback, representing the profiles in terms of a research paper topic ontology. A novel profile visualization approach is taken to acquire profile feedback. Research papers are classified using ontological classes and collaborative recommendation algorithms used to recommend papers seen by similar people on their current topics of interest. Two small-scale experiments, with 24 subjects over 3 months, and a large-scale experiment, with 260 subjects over an academic year, are conducted to evaluate different aspects of our approach. Ontological inference is shown to improve user profiling, external ontological knowledge used to successfully bootstrap a recommender system and profile visualization employed to improve profiling accuracy. The overall performance of our ontological recommender systems are also presented and favourably compared to other systems in the literature.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/3baab859ecf3db59334251b01258b40ce1298e06

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Contextual Combinatorial Bandit and its Application on Diversified Online Recommendation (2014, background): “On one hand, some users may not provide sufficient records, in which case it is crucial to predict user preference dynamically according to user feedback [16, 17].”
Research-paper recommender systems: a literature survey (2015, methodology): “showed that profile feedback is better than relevance feedback: allowing users to edit their user models is more effective than just learning from relevance feedback [94].”
Improving recommendation lists through topic diversification (2005, methodology): “Among all non-accuracy evaluation metrics, coverage has been the most frequently used [11, 19, 9].”
Content-based Recommender Systems: State of the Art and Trends (2011, methodology): “Foxtrot [58] extends the Quickstep system by implementing a paper search interface, a profile visualization interface and an email notification, in addition to the Web page recommendation interface.”
Recommender Systems (2016, neutral): “The earliest work on evaluation with user studies may be found in [339, 385, 433].”
Recommender system application developments: A survey (2015, methodology): “Foxtrot e-resource k-Nearest classification Web-based Individual 2002 [141]”
Recommender systems survey (2013, methodology): “[159] propose using knowledge-based techniques to solve the coldstart problem.”
Data Mining for Web Personalization (2007, methodology): “[77] use an ontological profile for a user within their research paper recommendation system, QuickStep.”
Facing the cold start problem in recommender systems (2014, neutral): “Various techniques have been used in CB models like keyword-based models (Asnicar & Tasso, 1997; Chen & Sycara, 1998; Mladenic, 1999; Moukas, 1997), semantic techniques (Basile, de Gemmis, Gentile, Iaquinta, & Lops, 2007; De Gemmis et al., 2007; Eirinaki, Vazirgiannis, & Varlamis, 2003; Magnini & St”
Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions (2005, methodology): “For example, the Quickstep and Foxtrot systems [66] use research paper topic ontology to recommend online research articles to the users.”
User Models for Adaptive Hypermedia and Adaptive Educational Systems (2007, neutral): “For example, observed interest in machine learning causes increase of user interest in the parent concept artificial intelligence [128].”
Ontology-based news recommendation (2010, methodology): “Another difference lies in the construction of the user profile, as in [8], the user can adjust the profile.”