On building entity recommender systems using user click log and freebase knowledge

Yu, Xiao; Ma, Hao; Hsu, Bo-June; Han, Jiawei

doi:10.1145/2556195.2556233

Cited by 46 publications

(28 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dong et al (2012) use AUC and precision@30, and a variety of baselines, among which are Common Neighbors, Jaccard Index and Adamic Adar. Yu et al (2014) use mean reciprocal rank (MRR) and compare with simple heuristics such as global popularity and co-click. Zhang and Ansari (2013) use ROC and precision-recall curves, and compare with several methods among which, again, are Common Neighbors, Jaccard Index and Adamic Adar.…”

Section: Evaluation Methodsmentioning

confidence: 99%

“…Since it is more closely related to our work, we also mention a number of papers in which user features are augmented with semantic knowledge (Yu et al 2014;Kapanipathi et al 2014;Siehndel and Kawase 2012;Middleton et al 2004). A seminal work in this area is Middleton et al (2004), in which a manually defined topic ontology is used to recommend papers to academic staff and students.…”

Section: User Representationmentioning

confidence: 99%

“…A seminal work in this area is Middleton et al (2004), in which a manually defined topic ontology is used to recommend papers to academic staff and students. In Yu et al (2014), Freebase categories are used to represent movie description pages with a set of semantic features, such as actor, director, genre. The recommendation is based on temporal similarity between pages and a users click story.…”

Section: User Representationmentioning

confidence: 99%

See 2 more Smart Citations

Recommendation of microblog users based on hierarchical interest profiles

Faralli

Stilo

Velardi

2015

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Quite a number of recent works have concentrated on the task of recommending to Twitter users whom they should follow, among which, the WTF (Who To Follow) service provided by Twitter. Recommenders are based, either on the user's network structure, or on some notion of topical similarity with other users, or on both. In this paper, we propose to accomplish the recommendation task in two steps: First, we profile users and classify them as belonging to a target community (depending e.g., on their political affiliation, preferred football team, favorite coffee shop, etc.). Then, we fine-tune recommendations for selected populations. We cast both problems of user classification and recommendation as one of itemset mining, where items are either users' authoritative friends or semantic categories associated to friends, extracted from WiBi, the Wikipedia Bitaxonomy. In addition to evaluating our profiler and recommender on several populations, we also show that semantic categories allow for very finegrained population studies, and make it possible to recommend not only whom to follow, but also topics of interest, users interested in the same topic, and more.

show abstract

Section: Evaluation Methodsmentioning

confidence: 99%

Section: User Representationmentioning

confidence: 99%

Section: User Representationmentioning

confidence: 99%

See 1 more Smart Citation

Recommendation of microblog users based on hierarchical interest profiles

Faralli

Stilo

Velardi

2015

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

show abstract

“…Significant performance improvement has been achieved using concept and category information in Wikipedia to annotate the documents with enriched semantics information. Yu et al [81] explored a way to build personalized entity recommendation framework for search engine users by utilizing the knowledge extracted from Freebase. A user log dataset collected from a commercial search engine together with the entity graph ex tracted from Freebase are used to generate semantic enriched features and build up recommendation models.…”

Section: Oth Er Approach Es In Semantic Data Miningmentioning

confidence: 99%

Semantic data mining: A survey of ontology-based approaches

Dou

Wang

Liu

2015

Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015)

145

View full text Add to dashboard Cite

Semantic Data Mining refers to the data mining tasks that systematically incorporate domain knowledge, especially for mal semantics, into the process. In the past, many research efforts have attested the benefits of incorporating domain knowledge in data mining. At the same time, the proliferation of knowledge engineering has enriched the family of domain knowledge, espe cially formal semantics and Semantic Web ontologies. Ontology is an explicit specification of conceptualization and a formal way to define the semantics of knowledge and data. The formal structure of ontology makes it a nature way to encode domain knowledgefor the data mining use. In this survey paper, we introduce general concepts of semantic data mining. We investigate why ontology has the potential to help semantic data mining and how formal semantics in ontologies can be incorporated into the data mining process. We provide detail discussions for the advances and state of art of ontology-based approaches and an introduction of approaches that are based on other form of

show abstract

“…Recently, entity recommendation has received much attention in web search. Major search engines have recently published their work on recommending related entities to the user search query [3] [12]. In addition to the knowledge graph, search engines also utilize various resources such as Who Are the American Vegans Related to Brad Pitt?…”

Section: Related Workmentioning

confidence: 99%

Who are the American Vegans related to Brad Pitt?

Aggarwal

Asooja

Ziad

et al. 2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

In this demo, we present Entity Relatedness Graph (EnRG), a focused related entities explorer, which provides the users with a dynamic set of filters and facets. It gives a ranked lists of related entities to a given entity, and clusters them using the different filters. For instance, using EnRG, one can easily find the American vegans related to Brad Pitt or Irish universities related to Semantic Web. Moreover, EnRG helps a user in discovering the provenance for implicit relations between two entities. EnRG uses distributional semantics to obtain the relatedness scores between two entities.

show abstract

On building entity recommender systems using user click log and freebase knowledge

Cited by 46 publications

References 29 publications

Recommendation of microblog users based on hierarchical interest profiles

Recommendation of microblog users based on hierarchical interest profiles

Semantic data mining: A survey of ontology-based approaches

Who are the American Vegans related to Brad Pitt?

Contact Info

Product

Resources

About