At the SocVis Lab we use Computer and Information Sciences to study online individual and social behavior from an interdisciplinary view stand. We are interested in understanding how individuals and groups of people use online technology, and also in developing algorithms and applications to enhance the people's abilities to exploit those technologies. We focus on the following areas of research:
We use both quantitative and qualitative approaches in our research. Among the quantitative approaches we make extensive use of data mining algorithms and statistical analysis on off-line datasets to discover patterns of individual and social behaviors. We also perform user studies in order to test online our findings over off-line data analysis, where we combine qualitative and quantitave analysis.
We meet every Friday at 3:30 pm in the Computer Science Department (DCC) at PUC.
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".
Exponential Random Graph Models (ERGMs)have been referred to as a promising technique for the modeling of social networks (Snijders, 2007). Topics of this talk include examples of social networks modeling, the logic of ERGMs, parameter selection and estimation, parameter interpretation, Goodness of Fit, and troubleshooting convergence issues. This talk will be held Aug. 11 in room C404.
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.
Engineering Student Vicente Iruretagoyena has earned a 2-month research visit to University of Texas at Austin. Congratulations and good luck!
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.
Prof. Chaoli Wang from University of Notre Dame, USA gave a talk about The Role of Graphs in Scientific Visualization: From Visual interface to Analytics Tool. More information
Diana Hu, director of Data Science, Verizon on Cue gave a talk about recommendation systems in Verizon onCue. More information
Engineering Student Matias has earned a 2-month research visit to University of Texas at Austin. Matias was selected 1st among 25 students, congratulations and good luck!
Professor Denis Parra earned a 3-year grant from Chilean Research Agency Conicyt for research on the intersection between HCI + Recommender Systems. The project is called "Dealing with Information Overload Leveraging Intelligent User Interfaces for Recommender Systems"
Professor Leandro Balby-Marinho is a co-author of the best paper award at the ACM RecSys 2015 conference with the article "Context-Aware Event Recommendation in Event-based Social Networks" available at http://dl.acm.org/citation.cfm?id=2800187
Funding from PUC was granted to Prof. Parra for a 1-month academic visit to Prof. Chaoli Wang [http://www3.nd.edu/~cwang11/about.html] from Notre Dame in order to collaborate in Visual approaches for Graph-Based Recommender Systems.
We have two papers accepted at the ACM RecSys 2015 conference. "Good Times Bad Times: A Study on Recency Effects in Collaborative Filtering for Social Tagging"[pre-print pdf] and "Are Real-World Place Recommender Algorithms Useful in Virtual World Environments?" [pre-print pdf].
Our Journal paper submitted to the Computer Communications journal has been accepted! Check later for updates on it, "Twitter in Academic Events: A Study of Temporal Usage, Communication, Sentimental and Topical Patterns in 16 Computer Science Conferences"
Our two papers submitted to ACM RecSys 2015 have been accepted: "Good Times Bad Times: A Study on Recency Effects in Collaborative Filtering for Social Tagging" and "Are Real-World Place Recommender Algorithms Useful in Virtual World Environments". See you in Vienna!
Our project proposal “Visualization and Recommendation of Large Image and Text Collections toward Effective Sensemaking" has been granted but Andrónico Luksic fund. P.I. Professor Chaoli Wang Link (University of Notre Dame) will collaborate with Co-PI Professor Denis Parra (PUC Chile) on this emerging research topic to make recommendations on large graphs, extending Prof. Wang's work on iGraph Link
Our Workshop proposal at ACM SIGIR was accepted! We are organizing the International Workshop on Social Personalisation & Search co-located with ACM SIGIR 2015, see more details at http://socialcomputing.ing.puc.cl/sps2015/
Christoph Trattner got accepted two articles on WWW 2015 Web Science track and Denis has a workshop paper
See the papers below
Denis gives an Invited talk on Recommender Systems at the Chilean Computer Science Week. His slides are http://www.slideshare.net/denisparra/keynote-at-chilean-week-of-computer-science and information about his talk http://www.jcc2014.ucm.cl/en/
Chris starts his ERCIM fellowship at NTNU (Norwegian University of Science and Technology), he will continue collaborating from Trondheim!
Chris, Leandro and Denis have successfully co-organized the 1st International Workshop on Social Personalization colocated at ACM Hypertext 2014. Check more details here: http://columbus.exp.sis.pitt.edu/sp2014/
Sepulveda, G; Dominguez, V; Parra, D.
RecSys 2017 posters.
Domínguez, V; Messina, P; Parra, D; Mery, D; Trattner, C; Soto, A.
Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems.
del-Rio, F; Parra, D; Kuzmicic, J.; Svec, E.
RecSys 2017 posters.
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.
Workshop IntRS 2016, RecSys 2016
Workshop RecTour 2016, RecSys 2016
He, C.; Parra, D.; and Verbert, K. Expert Systems with Applications. 2016.
Andjelkovic, I.; Parra, D.; and O'Donovan, J. In Proceedings of the UMAP Conference, 2016. ACM
Eberhard, L. and Trattner, C.: Recommending Sellers to Buyers in Virtual Marketplaces Leveraging Social Information, In Proceedings of the ACM 2016 International Conference on World Wide Web Companion (WWW 2016), ACM, New York, NY, USA, 2016.
Atzmueller, M., Chin, A., Janssen, F., Schweizer, I. and Trattner, C. (Eds.): Big Data Analytics in the Social and Ubiquitous Context, Lecture Notes in Artificial Intelligence, Vol. 9546, Springer, 2016.
Trattner, C., Kusmierczyk, T., Norvag, K.: FOODWEB – Studying Food Consumption and Production Patterns on the Web, ERCIM NEWS (104), 2016
Trattner, C., Kowald, D., Seitlinger, P., Kopeinik, S. and Ley, T.: Modeling Activation Processes in Human Memory to Predict the Use of Tags in Social Bookmarking Systems, Journal of Web Science, 2016.
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.
Visualization and Recommendation of Large Image and Text Collections Toward Effective Sensemaking. Gu, Y.; Wang, C.; Ma, J.; Nemiroff, R. J.; Kao, D. L.; and Parra, D. Information Visualization (in press), . 2016.
Using QR codes to increase user engagement in museum-like spaces. Perez-Sanagustin, M.; Parra, D.; Verdugo, R.; Garcia-Galleguillos, G.; and Nussbaum, M. Computers in Human Behavior, . 2016.
Denis Parra, Christoph Trattner, Diego Gómez, Matías Hurtado, Xidao Wen, Yu-Ru Lin, Twitter in academic events: A study of temporal usage, communication, sentimental and topical patterns in 16 Computer Science conferences, Computer Communications, Available online 11 July 2015, ISSN 0140-3664, http://dx.doi.org/10.1016/j.comcom.2015.07.001
Keywords: Twitter; Academic conferences; Evolution over time; Topic models; Sentiment analysis
Santiago Larraín, Denis Parra, Alvaro Soto, "Towards Improving Top-N Recommendation by Generalization of SLIM" short paper accepted at ACM RecSys
Ruth García, Diego Gómez, Denis Parra, Christoph Trattner, Andreas Kaltenbrunner, Eduardo Graells-Garrido
"Language, Twitter and Academic Conferences" in Proceedings of ACM Conference in Hypertext and Social Media 2015, Cyprus.
Marinho, L., Trattner, C. and Parra, D.: Are Real-World Place Recommender Algorithms Useful in Virtual World Environments? on ACM RecSys 2015
Larrain, S., Parra, D., Trattner, C., Graells-Garrido, E., Norvag, K.: Good Times Bad Times: A Study on Recency Effects in Collaborative Filtering for Social Tagging on ACM RecSys 2015
Student Matías Hurtado has released a tutorial about DTM (Dynamic Topic Modelling). In this tutorial you can learn how to classify big data by topics over a timespan using DTM. Based on Blei, D. M., & Lafferty, J. D. (2006, June). Dynamic topic models. In Proceedings of the 23rd international
conference on Machine learning (pp. 113120). ACM.
Cobo, A., Parra, D., Navón, J.: Identifying Relevant Messages in a Twitter-based Citizen Channel for Natural Disaster Situations, In Proceedings of the The 3rd International Workshop on Social Web for Disaster Management (SWDM 2015), co-located at WWW 2015
PDF available | Dataset available
Kusmierczyk, T., Trattner, C and Norvag, K.: Temporal Patterns in Online Food Innovation, In Proceedings of the ACM 2015 International Conference on World Wide Web Companion (WWW 2015), ACM, New York, NY, USA, 2015
Kusmierczyk, T., Trattner, C and Norvag, K.: Temporality in Online Food Recipe Consumption and Production, In Proceedings of the ACM 2015 International Conference on World Wide Web Companion (WWW 2015), ACM, New York, NY, USA, 2015
Denis Parra, Peter Brusilovsky, User-controllable personalization: A case study with SetFusion, Int. J. Human-Computer Studies
Lacic, E., Kowald, D., Seitlinger, P., Trattner, C. and Parra, D.: Recommending Items in Social Tagging Systems Using Tag and Time Informations, In Proceedings of the 1st international Workshop Social Personalization (SP 2014) at ACM Hypertext, Santiago, Chile, 2014
Wen, X., Lin, Y., Trattner, C. and Parra, D.: Twitter in Academic Conferences: Usage, Networking and Participation over Time, In Proceedings of the ACM 2014 International Conference in Hypertext and Social Media (Hypertext 2014), ACM, New York, USA, 2014
Fondecyt 11150783: Dealing with information overload using intelligent recommender system interfaces. 2016-2018
Project web page
Project “Visualization and Recommendation of Large Image and Text Collections toward Effective Sensemaking", Andrónico Luksic Collaboration Grant proposal. PI: Prof. Chaoli Wang (University of Notre Dame), Co-PI: Prof Denis Parra (PUC Chile)
Vicuna Mackenna 4860
Edificio San Agustin, 4to piso