Current Projects Suicide prevenTion in sOcial Platforms in Spain

More people die by suicide than by car accidents: according to the most recent data available from the 2014 in Spain, the number of deaths by suicide doubles those caused by car accidents (3910 vs 1873). If we consider the European Region, we shall see that six countries are listed in the top 20 with the highest estimated suicide rates globally. Based on the current situation and the scarcity of initiatives regarding suicide, we hypothesize that “social media monitoring could help in suicide prevention and contribute to national suicide strategies”. Hence, the main goal of this proposal is to detect depressive tendencies which may lead to suicide to fill in the existing gap in monitoring and prevention on social networks in Spain.

Project funded by the Maria de Maetzu Program of the Spanish Government.

More information

Mining the Web of Scientific Publications

The main objective of this project is the extension and development of software and approaches as well as the creation of new datasets taht will facilitate the extraction and summarization of knowledge from scientific publications in different disciplines. The project is a collaboration between the Natural Language Processing Group and the Web Research Group.

Project funded by the Maria de Maetzu Program of the Spanish Government.

More information

Music meets Natural Language Processing

We aim at representing what humans say about music, discovering and extracting knowledge from available textual sources, instead of audio and symbolic sources, as it has been studied earlier. This knowledge can be exploited to create large-scale, high quality software libraries and datasets in the music domain. For this, we will combine complementary expertise from the PI and team members in both Music, Musicology and Music Information Retrieval, along with The Natural Language Processing Group.

Project funded by the Maria de Maetzu Program of the Spanish Government.

More information.


DysWebxia is a model that includes studies with more than 150 people with dyslexia using eye tracking to make the texts more readable by modifying the content and presentation of the text.

This research was conducted with funding from Generalitat de Calalunya (FI doctoral fellowship).

More information

SUPER: Social sensors for security assessments and proactive emergencies management

(Through Eurecat agreement)

SUPER is a joint effort of social media and security experts towards introducing a holistic, integrated and privacy-friendly approach to the use of social media in emergencies and security incidents.

This project has received funding from the European Union 7th Framework Programme for research, technological development and demonstration.

More Information

TYPES: Towards transparency and privacy in the online advertising business

(Through Eurecat agreement)

We define, implement and validate in pre-market status a holistic framework of technologies and tools that guarantees both transparency and privacy preservation by giving the end user control upon the info he/she is willing to share .

The project has received funding from the European Union Horizon 2020 Research and Innovation Programme.

More Information

Past Projects

(Short selection)

Privacy Alerts: Would it be ever possible to empower on-line social network users to control the confidentiality of their data?

The challenge is to alert and make users aware of which non-confidential information about themselves can lead to the discovery of their confidential information. The project is radical because data mining and machine learning techniques will not be used to characterize traits in social network users, but to enable users themselves to regulate the usage of their data and we believe that social-network providers would also benefit from offering users this control.

The project is funded by the Ministry of Science and Innovation of Spain (MICINN) (grant number TIN2013-49814-EXP).


This project is about modelling, designing and implementing a modular and extensible platform to collect, process and store Web data. The platform will have the following components:

(a) Recollection and extraction of Web data
(b) Object storage (data, metadata, views, and relations)
(c) Formal algebra for data processing including operations for information retrieval, similarity, ranking, management of objects, graphs and temporal sequences, and statistics
(d) Visualization of views and relations.

This project is funded by the Ministry of Science and Innovation of Spain (MICINN) (grant number TIN2009-14560-C03-01/02/03).

More information

Web Research Group, Universitat Pompeu Fabra. Barcelona (Spain) wrg [at] @WRG:UPF
Versión en Castellano