Second workshop on information heterogeneity and fusion in recommender systems (HetRec2011)

Cantador, Iván; Brusilovsky, Peter; Kuflik, Tsvi

doi:10.1145/2043932.2044016

Cited by 328 publications

(186 citation statements)

References 0 publications

Supporting

Mentioning

164

Contrasting

Unclassified

Order By: Relevance

“…We conducted a user study in which participants, recruited via social networking sites, were presented with sets of movies or musicians (no combinations of both) from the HetRec'11 social tagging datasets [1]. They were requested to freely state which emotions they considered as relevant for each item (movie or musician), thus manually (and collectively) creating emotion-oriented item profiles, which we considered as ground truth.…”

Section: Methodsmentioning

confidence: 99%

“…They generated 713 evaluation cases, assigning an average of 3.30 and 4.18 emotions to items in the movies and music domains, respectively. 1 To evaluate the quality of the emotion-oriented profiles generated by our methods with respect to the ground truth profiles, we compared them by means of the Precision at position k, P@k, which, for a particular item, is defined as the percentage of the top k emotions returned by a method that are relevant for the item, as stated by the users of our study. Table 6 shows average precision values of the different methods and a random emotion ranking method.…”

Section: Methodsmentioning

confidence: 99%

“…Formally, let an emotion be defined as in formula (1). For an item (object) , let be the item's tag-based profile, where corresponds to the tag of the item's folksonomy.…”

Section: Emotion-oriented Tag-based Profilesmentioning

confidence: 99%

See 2 more Smart Citations

Modeling Emotions with Social Tags

Fernández-Tobías

Cantador

Plaza

2013

User Modeling, Adaptation, and Personalization

View full text Add to dashboard Cite

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription Modeling Emotions with Social TagsIgnacio Fernández-Tobías, Iván Cantador, Laura PlazaUniversidad Autónoma de Madrid, 28049 Madrid, Spain {i.fernandez, ivan.cantador, laura.plaza}@uam.es Abstract.We present an emotion model based on social tags, which is built upon an automatically generated lexicon that describes emotions by means of synonym and antonym terms. Using this model we develop a number of methods that transform social tag-based item profiles into emotion-oriented item profiles. We show that the model's representation of a number of basic emotions is in accordance with the well known psychological circumplex model of affect, and we report results from a user study that show a high precision of our methods to infer the emotions evoked by items in the movie and music domains.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Emotions with Social Tags

Fernández-Tobías

Cantador

Plaza

2013

User Modeling, Adaptation, and Personalization

View full text Add to dashboard Cite

show abstract

“…In addition to Freebase, the UBES system utilizes the usage data of the HetRec2011 MovieLens2k dataset [2]. With a simple heuristic based on IMDb identifiers, more than 10,000 out of 10,197 HetRec2011 movies have been matched to Freebase identifiers (cf.…”

Section: Usage-based Entity Summarization (Ubes)mentioning

confidence: 99%

Evaluating Entity Summarization Using a Game-Based Ground Truth

Thalhammer

Knuth

Sack

2012

The Semantic Web – ISWC 2012

View full text Add to dashboard Cite

Abstract. In recent years, strategies for Linked Data consumption have caught attention in Semantic Web research. For direct consumption by users, Linked Data mashups, interfaces, and visualizations have become a popular research area. Many approaches in this field aim to make Linked Data interaction more user friendly to improve its accessibility for nontechnical users. A subtask for Linked Data interfaces is to present entities and their properties in a concise form. In general, these summaries take individual attributes and sometimes user contexts and preferences into account. But the objective evaluation of the quality of such summaries is an expensive task. In this paper we introduce a game-based approach aiming to establish a ground truth for the evaluation of entity summarization. We exemplify the applicability of the approach by evaluating two recent summarization approaches.

show abstract

“…In our experimentations we use the MovieLens dataset and IMDb database, which are publicly available [9]. The tests have been performed for: (1) analysing the pertinence of bloom filters in recommender systems, (2) enhancing the usage of a bitwise AND similarity instead of the common vector cosine/jaccard similarities and (3) using a bitwise XNOR similarity.…”

Section: Introductionmentioning

confidence: 99%