SocVis Social Computing & Visualization Group. SoCo: Social Computing, RS: Recommender Systems, UM: User Modeling, Pe: Personalization, Vis: Visualization

Fondecyt 11150783: Dealing with information overload using intelligent recommender system interfaces. (2016-2018)


Nowadays, the amount of information that can be accessed on the Web is so vast and grows so quickly that finding the most relevant data to solve our personal information needs has become an extremely dificult problem. The area of recommender systems has risen in order to provide the best tools for users to tackle the information overload problem within any context and in a personalized manner. Companies like, or Netflix rely on recommendation algorithms to engage users in their services by suggesting them products and movies. Despite their success, recommender systems face several challenges in terms of user satisfaction and acceptance of the items suggested. This problem is due to the fact that user satisfaction is not only related to the algorithmic accuracy of the predicted recommendations, but also to other factors, such as explainability the system explains the reasons behind suggested items and recommendation diversity. In our previous research in the subfield of user-centric recommender systems, we have proven that giving users control over the recommendation mechanisms through exploratory interfaces, improves their understanding of the recommendations and hence, their engagement and satisfaction. However, there is insuficient research that systematically analyzes user-controlled interactive exploratory interfaces, which go beyond the traditional way of presenting recommendations with ranked lists. Following this motivation, we propose this project that integrates Human-Computer Interaction (HCI) with recommender systems algorithms. Our objective is to determine which combination of recommender algorithms, user traits, and contextual factors make intelligent user interfaces more effective for personalized information filtering.

Our goals are:


Miercoles 18 Julio 2018

Charla de investigadora invitada

La doctora en Computación y colaboradora del proyecto, María Jesús Lobo, presentará la charla "Transiciones Interactivas para Aplicaciones Cartográficas". Más información en

Friday 30 March 2018

Award in ACM IUI Conference: Honorable mention for Ivania Donoso!

The master student Ivania Donoso, who presented her research at the ACM Conference on Intelligent User Interfaces in Tokyo, Japan, was awarded a honorable mention as candidate for the best paper! check the paper at the ACM DL: An Interactive Relevance Feedback Interface for Evidence-Based Health Care .

Tuesday 1 August 2017

Professor Denis Parra and graduate students will be presenting their work at RecSys 2017

Vicente Dominguez, Pablo Messina, Prof. Denis Parra, Prof. Domingo Mery, Prof. Christoph Trattner and Prof. Alvaro Soto will be presenting their work titled "Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation".

Monday 3 July 2017

Professor Trattner visits SocVis

We are glad to receive the visit of our collaborator Professor Christoph Trattner from Austria. He will be working with us from 5 to 12 of July 2017.

Wednesday 13 July 2016

Professor Parra gave two keynote talks at futurePD and IFUP workshops

Professor Parra gave a keynot talk on FUTUREPD – THE FUTURE OF PERSONAL DATA and on IFUP: Workshop on Multi-dimensional Information Fusion for User Modeling and Personalization during his visit to Canada.

Monday 9 May 2016

Professor Parra introduces Moodplay in the Chilean news

EMOL - La Tercera - Diario Financiero - Ingeniería PUC



Graduate Students

Technical Personnel



Content-based artwork recommendation: integrating painting metadata with neural and manually-engineered visual features

Messina, P., Dominguez, V., Parra, D., Trattner, C., & Soto, A. (2018). Content-based artwork recommendation: integrating painting metadata with neural and manually-engineered visual features. User Modeling and User-Adapted Interaction, 1-40.
PDF available | DOI

Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation

Domínguez, V; Messina, P; Parra, D; Mery, D; Trattner, C; Soto, A. Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems.
PDF available

Monitoring obesity prevalence in the US through bookmarking activities in online food portals

Trattner, C., Parra, D., & Elsweiler, D. (2017). Monitoring obesity prevalence in the US through bookmarking activities in online food portals. PloS one, 12(6), e0179144.
PDF available

Scalable Exploration of Relevance Prospects to Support Decision Making

Workshop IntRS 2016, RecSys 2016
PDF available

Understanding the Impact of Weather for POI Recommendations

Workshop RecTour 2016, RecSys 2016
PDF available

Interactive recommender systems: a survey of the state of the art and future research challenges and opportunities

He, C.; Parra, D.; and Verbert, K. Expert Systems with Applications. 2016.
PDF Available

Moodplay: Interactive Mood-based Music Discovery and Recommendation.

Andjelkovic, I.; Parra, D.; and O'Donovan, J. In Proceedings of the UMAP Conference, 2016. ACM
PDF Available


Contact Us

Name Email Comments

Mailing address

Denis Parra
Vicuna Mackenna 4860
Edificio San Agustin, 4to piso
Macul 7820436