HappyMovie: A Facebook Application for Recommending Movies to Groups

Quijano-Sánchez, Lara; Recio-Garcí­a, Juan A.; Dí­az-Agudo, Belén

doi:10.1109/ictai.2011.44

Cited by 31 publications

(27 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Users have to move an arrow showing their degree of similarity with the personality characteristics of the characters being presented (these personality characteristics along with examples of typical behaviour patterns are presented under each character's image). In [13] we concluded that it is possible to replace the TKI personality test with the movie metaphor test because it provides an statistically The results that the TKI test provided for the five different personality modes in comparison with the values that the movie metaphor test gathered had a Mean Absolute Error (MAE) [52] of 0.12. Hence, we believe that it is worth sacrificing a little accuracy in the test results (as they are not for psychology testing purposes) in exchange of enhancing significantly the usability and interest for the application.…”

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 97%

“…Hence, although we cannot conclude this section with a design prescription, we are comfortable enough in presenting it as a useful estimation of the tie strength between users 13 .…”

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 99%

“…These weights will also be influenced by the different personalities of each group member. For example, a user who dislikes the movie (gives it a low rating) may nevertheless be satisfied with the recommendation, especially if s/he 13 We are currently performing an experiment with HappyMovie's users where, after obtaining users' real trust value through enquiries, we use a genetic algorithm to adjust the weights of each variable. Our goal is to achieve the minimum MAE when comparing the real trust value given by users to the estimation that HappyMovie provides.…”

Section: Long Term Knowledge Management Modulesmentioning

confidence: 99%

“…Our content-based method applies a weighted average of the similarity of the following fields that describe each movie: duration (w 1 = 0.01), recommended age (w 2 = 0.03), nationality (w 3 = 0.11), actors (w 4 = 0.17), directors (w 5 = 0.178), percentage of action 15 The first time that we implemented this test [13], we chose wellknown classic movies, however they were no good for the recommender as it compares actors and directors, besides genre, etc, from current movies on cinemas. So, if for example we selected Marilyn Monroe movies the actor's field would be useless as she is no longer making movies and there would not be any possible comparison between fields.…”

Section: Content Based Estimationmentioning

confidence: 99%

“…This survey provides a self-contained full description to support the complete reproducibly of our system. In [13] we presented a functional vision of HappyMovie. This previous work introduced an initial version of HappyMovie where the focus was on presenting an experiment on the viability of making the application more easy going through an interactive game that measures users' personality instead of the long questionnaire that we previously used in [10,11].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Development of a group recommender application in a Social Network

Quijano-Sánchez

Díaz-Agudo

Recio-García

2014

Knowledge-Based Systems

View full text Add to dashboard Cite

In today's society, recommendations are becoming increasingly important. With the advent of the Social Web and the growing popularity of Social Networks, where users explicitly provide personal information and interact with others and the system, it is becoming clear that the key for the success of recommendations is to develop new strategies which focus on social recommendations leveraged by these new sources of knowledge. In our work, we focus on group recommender systems. These systems traditionally suffer from a number of shortcomings that hamper their effectiveness. In this paper we continue our research, that focuses on improving the overall quality of group recommendations through the addition of social knowledge to existing recommendation strategies. To do so, we use the information stored in Social Networks to elicit social factors following two approaches: the cognitive modeling approach, that studies how people's way of thinking predisposes their actions; and the social approach, that studies how people's relationships predispose their actions. We show the value of using models of social cognition extracted from Social Networks in group recommender systems through the instantiation of our model into a real-life Facebook movie recommender application.

show abstract

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 97%

“…Hence, although we cannot conclude this section with a design prescription, we are comfortable enough in presenting it as a useful estimation of the tie strength between users 13 .…”

Section: Social Knowledge Elicitation Modulesmentioning

confidence: 99%

Section: Long Term Knowledge Management Modulesmentioning

confidence: 99%

Section: Content Based Estimationmentioning

confidence: 99%