Guangyuan Piao

Measuring semantic distance for linked open data-enabled recommender systems

The Linked Open Data (LOD) initiative has been quite successful in terms of publishing and interlinking data on the Web. On top of the huge amount of interconnected data, measuring relatedness between resources and identifying their relatedness could be used for various applications such as LOD-enabled recommender systems. In this paper, we propose various distance measures, on top of the basic concept of Linked Data Semantic Distance (LDSD), for calculating Linked Data semantic distance between resources that can be used in a LOD-enabled recommender system. We evaluated the distance measures in the context of a recommender system that provides the top-N recommendations with baseline methods such as LDSD. Results show that the performance is significantly improved by our proposed distance measures incorporating normalizations that use both of the resources and global appearances of paths in a graph.

Exploring Dynamics and Semantics of User Interests for User Modeling on Twitter for Link Recommendations

User modeling for individual users on the Social Web plays an important role and is a fundamental step for personalization as well as recommendations. Recent studies have proposed different user modeling strategies considering various dimensions such as temporal dynamics and semantics of user interests. Although previous work proposed different user modeling strategies considering the temporal dynamics of user interests, there is a lack of comparative studies on those methods and therefore the comparative performance over each other is unknown. In terms of semantics of user interests, background knowledge from DBpedia has been explored to enrich user interest profiles so as to reveal more information about users. However, it is still unclear to what extent different types of information from DBpedia contribute to the enrichment of user interest profiles. In this paper, we propose user modeling strategies which use Concept Frequency - Inverse Document Frequency (CF-IDF) as a weighting scheme and incorporate either or both of the dynamics and semantics of user interests. To this end, we first provide a comparative study on different user modeling strategies considering the dynamics of user interests in previous literature to present their comparative performance. In addition, we investigate different types of information (i.e., categories, classes and connected entities via various properties) for entities from DBpedia and the combination of them for extending user interest profiles. Finally, we build our user modeling strategies incorporating either or both of the best-performing methods in each dimension. Results show that our strategies outperform two baseline strategies significantly in the context of link recommendations on Twitter.

Analyzing Aggregated Semantics-enabled User Modeling on Google+ and Twitter for Personalized Link Recommendations

In this paper, we study if reusing Google+ profiles can provide reliable recommendations on Twitter to resolve the cold start problem. Next, we investigate the impact of giving different weights for aggregating user profiles from two OSNs and present that giving a higher weight to the targeted OSN profile for aggregation allows the best performance in the context of a personalized link recommender system. Finally, we propose a user modeling strategy which combines entity-and category-based user profiles using with a discounting strategy. Results show that our proposed strategy improves the quality of user modeling significantly compared to the baseline method.

Inferring User Interests for Passive Users on Twitter by Leveraging Followee Biographies

User modeling based on the user-generated content of users on social networks such as Twitter has been studied widely, and has been used to provide personalized recommendations via inferred user interest profiles. Most previous studies have focused on active users who actively post tweets, and the corresponding inferred user interest profiles are generated by analyzing these users’ tweets. However, there are also a great number of passive users who only consume information from Twitter but do not post any tweets. In this paper, we propose a user modeling approach using the biographies (i.e., self descriptions in Twitter profiles) of a user’s followees (i.e., the accounts that they follow) to infer user interest profiles for passive users. We evaluate our user modeling strategy in the context of a link recommender system on Twitter. Results show that exploring the biographies of a user’s followees improves the quality of user modeling significantly compared to two state-of-the-art approaches leveraging the names and tweets of followees.

Computing the Semantic Similarity of Resources in DBpedia for Recommendation Purposes

The Linked Open Data cloud has been increasing in popularity, with DBpedia as a first-class citizen in this cloud that has been widely adopted across many applications. Measuring similarity between resources and identifying their relatedness could be used for various applications such as item-based recommender systems. To this end, several similarity measures such as LDSD (Linked Data Semantic Distance) were proposed. However, some fundamental axioms for similarity measures such as “equal self-similarity”, “symmetry” or “minimality” are violated, and property similarities have been ignored. Moreover, none of the previous studies have provided a comparative study on other similarity measures. In this paper, we present a similarity measure, called Resim (Resource Similarity), based on top of a revised LDSD similarity measure. Resim aims to calculate the similarity of any resources in DBpedia by taking into account the similarity of the properties of these resources as well as satisfying the fundamental axioms. In addition, we evaluate our similarity measure with two state-of-the-art similarity measures (LDSD and Shakti) in terms of calculating the similarities for general resources (i.e., any resources without a domain restriction) in DBpedia and resources for music artist recommendations. Results show that our similarity measure can resolve some of the limitations of state-of-the-art similarity measures and performs better than them for calculating the similarities between general resources and music artist recommendations.

Towards Comprehensive User Modeling on the Social Web for Personalized Link Recommendations

User modeling for individual users on the Social Web plays a significant role and is a fundamental step for personalization as well as recommendations. Previous studies have proposed various user modeling strategies in different dimensions such as (1) interest representation, (2) interest propagation, (3) content enrichment and (4) temporal dynamics of user interests. This research mainly focuses on the first two dimensions interest representation and propagation. In addition, we also investigate the combination of these four dimensions and their synergistic effect on the quality of user modeling. Different user modeling strategies will then be evaluated in the context of personalized link recommender systems using standard evaluation methodologies such as Mean Reciprocal Rank (MRR), recall (R@N) and success (S@N) at rank N.

User Modeling on Twitter with WordNet Synsets and DBpedia Concepts for Personalized Recommendations

User modeling of individual users on the Social Web platforms such as Twitter plays a significant role in providing personalized recommendations and filtering interesting information from social streams. Recently, researchers proposed the use of concepts (e.g., DBpedia entities) for representing user interests instead of word-based approaches, since Knowledge Bases such as DBpedia provide cross-domain background knowledge about concepts, and thus can be used for extending user interest profiles. Even so, not all concepts can be covered by a Knowledge Base, especially in the case of microblogging platforms such as Twitter where new concepts/topics emerge everyday. In this short paper, instead of using concepts alone, we propose using synsets from WordNet and concepts from DBpedia for representing user interests. We evaluate our proposed user modeling strategies by comparing them with other bag-of-concepts approaches. The results show that using synsets and concepts together for representing user interests improves the quality of user modeling significantly in the context of link recommendations on Twitter.

Interest Representation, Enrichment, Dynamics, and Propagation: A Study of the Synergetic Effect of Different User Modeling Dimensions for Personalized Recommendations on Twitter

Microblogging services such as Twitter have been widely adopted due to the highly social nature of interactions they have facilitated. With the rich information generated by users on these services, user modeling aims to acquire knowledge about a users interests, which is a fundamental step towards personalization as well as recommendations. To this end, researchers have explored different dimensions such as 1 Interest Representation, 2 Content Enrichment, 3 Temporal Dynamics of user interests, and 4 Interest Propagation using semantic information from a knowledge base such as DBpedia. However, those dimensions of user modeling have largely been studied separately, and there is a lack of research on the synergetic effect of those dimensions for user modeling. In this paper, we address this research gap by investigating 16 different user modeling strategies produced by various combinations of those dimensions. Different user modeling strategies are evaluated in the context of a personalized link recommender system on Twitter. Results show that Interest Representation and Content Enrichment play crucial roles in user modeling, followed by Temporal Dynamics. The user modeling strategy considering Interest Representation, Content Enrichment and Temporal Dynamics provides the best performance among the 16 strategies. On the other hand, Interest Propagation has little effect on user modeling in the case of leveraging a rich Interest Representation or considering Content Enrichment.

Inferring user interests in microblogging social networks: a survey

With the growing popularity of microblogging services such as Twitter in recent years, an increasing number of users are using these services in their daily lives. The huge volume of information generated by users raises new opportunities in various applications and areas. Inferring user interests plays a significant role in providing personalized recommendations on microblogging services, and also on third-party applications providing social logins via these services, especially in cold-start situations. In this survey, we review user modeling strategies with respect to inferring user interests from previous studies. To this end, we focus on four dimensions of inferring user interest profiles: (1) data collection, (2) representation of user interest profiles, (3) construction and enhancement of user interest profiles, and (4) the evaluation of the constructed profiles. Through this survey, we aim to provide an overview of state-of-the-art user modeling strategies for inferring user interest profiles on microblogging social networks with respect to the four dimensions. For each dimension, we review and summarize previous studies based on specified criteria. Finally, we discuss some challenges and opportunities for future work in this research domain.

Analyzing MOOC Entries of Professionals on LinkedIn for User Modeling and Personalized MOOC Recommendations

The main contribution of this work is the comparison of three user modeling strategies based on job titles, educational fields and skills in LinkedIn profiles, for personalized MOOC recommendations in a cold start situation. Results show that the skill-based user modeling strategy performs best, followed by the job- and edu-based strategies.