Ernesto Diaz-Aviles

Cross-tagging for personalized open social networking

The Social Web is successfully established and poised for continued growth. Web 2.0 applications such as blogs, bookmarking, music, photo and video sharing systems are among the most popular; and all of them incorporate a social aspect, i.e., users can easily share information with other users. But due to the diversity of these applications -- serving different aims -- the Social Web is ironically divided. Blog users who write about music for example, could possibly benefit from other users registered in other social systems operating within the same domain, such as a social radio station. Although these sites are two different and disconnected systems, offering distinct services to the users, the fact that domains are compatible could benefit users from both systems with interesting and multi-faceted information. In this paper we propose to automatically establish social links between distinct social systems through cross-tagging, i.e., enriching a social system with the tags of other similar social system(s). Since tags are known for increasing the prediction quality of recommender systems (RS), we propose to quantitatively evaluate the extent to which users can benefit from cross-tagging by measuring the impact of different cross-tagging approaches on tag-aware RS for personalized resource recommendations. We conduct experiments in real world data sets and empirically show the effectiveness of our approaches.

Swarming to rank for information retrieval

This paper presents an approach to automatically optimize the retrieval quality of ranking functions. Taking a Swarm Intelligence perspective, we present a novel method, Swarm-Rank, which is well-founded in a Particle Swarm Optimization framework. SwarmRank learns a ranking function by optimizing the combination of various types of evidences such content and hyperlink features, while directly maximizing Mean Average Precision, a widely used evaluation measure in Information Retrieval. Experimental results on well-established Learning To Rank benchmark datasets show that our approach significantly outperformed standard approaches (i.e., BM25) that only use basic statistical information derived from documents collections, and is found to be competitive with Ranking SVM and RankBoost in the task of ranking relevant documents at the very top positions.

Tracking Twitter for epidemic intelligence: case study: EHEC/HUS outbreak in Germany, 2011

In the presence of sudden outbreaks, how can social media streams be used to strengthen surveillance capacity? In May 2011, Germany reported one of the largest described outbreaks of Enterohemorrhagic Escherichia coli (EHEC). The Shiga toxin-producing strain O104:H4 infected several thousand people, frequently leading to haemolytic uremic syndrome (HUS) and gastroenteritis (GI). By the end of June, 47 persons had died. In this work, we study the crowds behavior in Twitter during the outbreak. In particular, we present how Twitter can be exploited to support Epidemic Intelligence (EI) in the tasks of early warning, signal assessment and outbreak investigation. A user study with experts from the Robert Koch Institute, Germanys national-level public health authority, and from Lower Saxony State Health Department (NLGA) provide important insights towards the realization of an open early warning system based on Twitter, helping to realize the vision of Epidemic Intelligence for the Crowd, by the Crowd.

Towards personalized learning to rank for epidemic intelligence based on social media streams

In the presence of sudden outbreaks, how can social media streams be used to strengthen surveillance capabilities? In May 2011, Germany reported one of the largest described outbreaks of Enterohemorrhagic Escherichia coli (EHEC). By end of June, 47 persons had died. After the detection of the outbreak, authorities investigating the cause and the impact in the population were interested in the analysis of micro-blog data related to the event. Since Thousands of tweets related to this outbreak were produced every day, this task was overwhelming for experts participating in the investigation. In this work, we propose a Personalized Tweet Ranking algorithm for Epidemic Intelligence (PTR4EI), that provides users a personalized, short list of tweets based on the users context. PTR4EI is based on a learning to rank framework and exploits as features, complementary context information extracted from the social hash-tagging behavior in Twitter. Our experimental evaluation on a dataset, collected in real-time during the EHEC outbreak, shows the superior ranking performance of PTR4EI. We believe our work can serve as a building block for an open early warning system based on Twitter, helping to realize the vision of Epidemic Intelligence for the Crowd, by the Crowd.

LDA for on-the-fly auto tagging

In this paper, we propose a method for automatic tagging sparse and short textual resources. In the presence of a new resource, our method creates an ad hoc corpus of related resources, then applies Latent Dirichlet Allocation (LDA) to elicit latent topics for the resource and the associated corpus. This is done in order to automatically tag the resource based on the most likely tags derived from the latent topics identified. We evaluate our method, using an offline analysis on publicly available BibSonomy dataset and an online study, showing its effectiveness.

Taking the Pulse of Political Emotions in Latin America Based on Social Web Streams

Social media services have become increasingly popular and their penetration is worldwide. Micro-blogging services, such as Twitter, allow users to express themselves, share their emotions and discuss their daily life affairs in real-time, covering a variety of different points of view and opinions, including political and event-related topics such as immigration, economic issues, tax policy or election campaigns. On the other hand, traditional methods tracking public opinion still heavily rely upon opinion polls, which are usually limited to small sample sizes and can incur in significant costs in terms of time and money. In this paper, we leverage state-of-the-art techniques of sentiment analysis for real-time political emotion tracking. In particular, we analyze mentions of personal names of 18 presidents in Latin America, and measure each political figures effect in the emotions reflected on the social web.

Swarming to rank for recommender systems

Recommender systems make product suggestions that are tailored to the users individual needs and represent powerful means to combat information overload. In this paper, we focus on the item prediction task of Recommender Systems and present SwarmRankCF, a method to automatically optimize the performance quality of recommender systems using a Swarm Intelligence perspective. Our approach, which is well-founded in a Particle Swarm Optimization framework, learns a ranking function by optimizing the combination of unique characteristics (i.e., features) of users, items and their interactions. In particular, we build feature vectors from a factorization of the user-item interaction matrix, and directly optimize Mean Average Precision metric in order to learn a linear ranking model for personalized recommendations. Our experimental evaluation, on a real world online radio dataset, indicates that our approach is able to find ranking functions that significantly improve the performance of the system for the Top-N recommendation task.

Mining emotions in short films: user comments or crowdsourcing?

Short films are regarded as an alternative form of artistic creation, and they express, in a few minutes, a whole gamma of different emotions oriented to impact the audience and communicate a story. In this paper, we exploit a multi-modal sentiment analysis approach to extract emotions in short films, based on the film criticism expressed through social comments from the video-sharing platform YouTube. We go beyond the traditional polarity detection (i.e., positive/negative), and extract, for each analyzed film, four opposing pairs of primary emotions: joy-sadness, anger-fear, trust-disgust, and anticipation-surprise. We found that YouTube comments are a valuable source of information for automatic emotion detection when compared to human analysis elicited via crowdsourcing.

Living analytics methods for the web observatory

The collective effervescence of social media production has been enjoying a great deal of success in recent years. The hundred of millions of users who are actively participating in the Social Web are exposed to ever-growing amounts of sites, relationships, and information. In this paper, we report part of the efforts towards the realization of a Web Observatory at the L3S Research Center (www.L3S.de). In particular, we present our approach based on Living Analytics methods, whose main goal is to capture people interactions in real-time and to analyze multidimensional relationships, metadata, and other data becoming ubiquitous in the social web, in order to discover the most relevant and attractive information to support observation, understanding and analysis of the Web. We center the discussion on two areas: (i) Recommender Systems for Big Fast Data and (ii) Collective Intelligence, both key components towards an analytics toolbox for our Web Observatory.

Self-supervised detection of disease reporting events in outbreak reports

State-of-the-art supervised approaches for automatically detecting disease reporting events are typically constructed using manual training examples. Such systems suffer from high initial, and sustainability costs.