Ontological technologies for user modelling

Sosnovsky, Sergey; Dicheva, Darina

doi:10.1504/ijmso.2010.032649

Cited by 68 publications

(37 citation statements)

References 137 publications

(118 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Computing time for CF tends to be higher than for content-based filtering [264]. Collaborative filtering is generally less scalable and requires more offline data processing than CBF [331]. Torres et al note that collaborative filtering creates similar users [117] and Sundar et al observe that collaborative filtering dictates opinions [332].…”

Section: Collaborative Filteringmentioning

confidence: 99%

Research-paper recommender systems: a literature survey

et al. 2015

View full text Add to dashboard Cite

In the last 16 years, more than 200 research articles were published about research-paper recommender systems. We reviewed these articles and present some descriptive statistics in this paper, as well as a discussion about the major advancements and shortcomings and an overview of the most common recommendation concepts and approaches. We found that more than half of the recommendation approaches applied content-based filtering (55 %). Collaborative filtering was applied by only 18 % of the reviewed approaches, and graph-based recommendations by 16 %. Other recommendation concepts included stereotyping, item-centric recommendations, and hybrid recommendations. The content-based filtering approaches mainly utilized papers that the users had authored, tagged, browsed, or downloaded. TF-IDF was the most frequently applied weighting scheme. In addition to simple terms, n-grams, topics, and citations were utilized to model users' information needs. Our review revealed some shortcomings of the current research. First, it remains unclear which recommendation concepts and approaches are the most promising. For instance, researchers reported different results on the performance of contentbased and collaborative filtering. Sometimes content-based filtering performed better than collaborative filtering and Linnaeus University, Kalmar, Sweden sometimes it performed worse. We identified three potential reasons for the ambiguity of the results. (A) Several evaluations had limitations. They were based on strongly pruned datasets, few participants in user studies, or did not use appropriate baselines. (B) Some authors provided little information about their algorithms, which makes it difficult to re-implement the approaches. Consequently, researchers use different implementations of the same recommendations approaches, which might lead to variations in the results. (C) We speculated that minor variations in datasets, algorithms, or user populations inevitably lead to strong variations in the performance of the approaches. Hence, finding the most promising approaches is a challenge. As a second limitation, we noted that many authors neglected to take into account factors other than accuracy, for example overall user satisfaction. In addition, most approaches (81 %) neglected the user-modeling process and did not infer information automatically but let users provide keywords, text snippets, or a single paper as input. Information on runtime was provided for 10 % of the approaches. Finally, few research papers had an impact on research-paper recommender systems in practice. We also identified a lack of authority and long-term research interest in the field: 73 % of the authors published no more than one paper on research-paper recommender systems, and there was little cooperation among different co-author groups. We concluded that several actions could improve the research landscape: developing a common evaluation framework, agreement on the information to include in research papers, a stronger focus on non-accuracy aspect...

show abstract

Section: Collaborative Filteringmentioning

confidence: 99%

Research-paper recommender systems: a literature survey

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Dolog and Schäfer (2005) developed a framework for browsing, manipulating and maintaining interoperable learner profiles which provided a common base for the exchange of learner profiles between several sources. Ontological technologies for user modelling were adopted by Sosnovsky and Dicheva (2010) to translate overlay student models for relative domains by means of ontology mapping. Furthermore, semantic web technologies were also linked to open user models.…”

Section: Open Learner Modelling Approaches That Utilise Semantic Web mentioning

confidence: 99%

From Interactive Open Learner Modelling to Intelligent Mentoring: STyLE-OLM and Beyond

Dimitrova

Brna

2015

Int J Artif Intell Educ

View full text Add to dashboard Cite

STyLE-OLM (Dimitrova 2003 International Journal of Artificial Intelligence in Education, 13, 35-78) presented a framework for interactive open learner modelling which entails the development of the means by which learners can inspect, discuss and alter the learner model that has been jointly constructed by themselves and the system. This paper outlines the STyLE-OLM framework and reflects on the key challenges it addressed: (a) the design of an appropriate communication medium; this was addressed by proposing a structured language using diagrammatic representations of conceptual graphs; (b) the management of the interaction with the learner; this was addressed by designing a framework for interactive open learner modelling dialogue utilising dialogue games; (c) the accommodation of different beliefs about the learner's domain model; this was addressed with a mechanism for maintaining different views about the learner beliefs which adapted belief modal logic operators; and (d) the assessment of any resulting improvements in learner model accuracy and learner reflection; this was addressed in a user study with an instantiation of STyLE-OLM for diagnosing a learner's knowledge of finance concept, as part of a larger project that developed an intelligent system to assist with learning domain terminology in a foreign language. Reviewing follow on work, we refer to projects by the authors' students and colleagues leading to further extension and adoption of STyLE-OLM, as well as relevant approaches in open learner modelling which have cited the STyLE-OLM framework. The paper points at outstanding research challenges and outlines future a research direction to extend interactive open learner modelling towards mentor-like intelligent learning systems.

show abstract

“…However, instructional planning on a macro-level has not been approached as a problem of persuasive intervention design or incentive mechanism design. Using concept maps of the subject area (Sosnovsky and Dicheva 2010) and AI planning techniques, paths for achieving particular learning goals can be generated. Previous work on course sequencing and dynamic courseware generation (Vassileva and Deters 1998;Brusilovsky and Vassileva 2003) can be used as a basis to inform content goal generation with integrated rewards to generate personalized learning plans.…”

Section: Bridging Open User Modeling and Social Visualizationmentioning

confidence: 99%

Motivating participation in social computing applications: a user modeling perspective

Vassileva

2012

User Model User-Adap Inter

183

112

View full text Add to dashboard Cite

The explosive growth of Web-based social applications over the last 10 years has led people to engage in online communities for various purposes: to work, learn, play, share time and mementos with friends and family and engage in public action. Social Computing Applications (SCA) allow users to discuss various topics in online forums, share their thoughts in blogs, share photos, videos, bookmarks, and connect with friends through social networks. Yet, the design of successful social applications that attract and sustain active contribution by their users still remains more of an art than a science. My research over the last 10 years has been based on the hypothesis that it is possible to incorporate mechanisms and tools in the design of the social application that can motivate users to participate, and more generally, to change their behavior in a desirable way, which is beneficial for the community. Since different people are motivated by different things, it can be expected that personalizing the incentives and the way the rewards are presented to the individual, would be beneficial. Also since communities have different needs in different phases of their existence, it is necessary to model the changing needs of communities and adapt the incentive mechanisms accordingly, to attract the kind of contributions that are beneficial. Therefore User and Group (Community) Modeling is an important area in the design of incentive mechanisms. This paper presents an overview of different approaches to motivate users to participate. These approaches are based on various theories from the area of social psychology and behavioral economics and involve rewards mechanisms, reputation, open group user modeling, and social visualization. Future trends are outlined towards convergence with the areas of persuasive systems design, adaptive/personalized systems, and intelligent social learning environments.

show abstract

Ontological technologies for user modelling

Cited by 68 publications

References 137 publications

Research-paper recommender systems: a literature survey

Research-paper recommender systems: a literature survey

From Interactive Open Learner Modelling to Intelligent Mentoring: STyLE-OLM and Beyond

Motivating participation in social computing applications: a user modeling perspective

Contact Info

Product

Resources

About