<div dir="ltr"><div style="text-align:center">********************************************************************</div><div style="text-align:center"> </div><div style="text-align:center">SEPLN 2013 workshop on:</div><div style="text-align:center">
</div><div style="text-align:center">Sentiment Analysis at SEPLN</div><div style="text-align:center">(TASS 2013)</div><div style="text-align:center"> </div><div style="text-align:center"> </div><div style="text-align:center">
Sep 20, 2013</div><div style="text-align:center">Madrid, Spain</div><div style="text-align:center"> </div><div style="text-align:center"><a href="http://www.daedalus.es/TASS2013/dates.php">http://www.daedalus.es/TASS2013/dates.php</a></div>
<div style="text-align:center"> </div><div style="text-align:center"> </div><div style="text-align:center">Registration: <a href="http://www.daedalus.es/TASS2013/tasks.php">http://www.daedalus.es/TASS2013/tasks.php</a></div>
<div style="text-align:center"> </div><div style="text-align:center"> </div><div style="text-align:center">********************************************************************</div><div style="text-align:center"> </div><div>
Currently market research using user surveys is typically performed. However, the rise of social media such as blogs and social networks and the increasing amount of user-generated contents in the form of reviews, recommendations, ratings and any other form of opinion, has led to creation of an emerging trend towards online reputation analysis. This analysis has two technological aspects: sentiment analysis and text classification (or categorization).</div>
<div><br></div><div>First, the so-called sentiment analysis, i.e., the application of natural language processing and text analytics to identify and extract subjective information from texts, which is the first step towards the online reputation analysis, is becoming a promising topic in the field of marketing and customer relationship management, as the social media and its associated word-of-mouth effect is turning out to be the most important source of information for companies and their customers' sentiments towards their brands and products.</div>
<div><br></div><div>Then, automatic text classification is used to guess the topic of the text, among those of a predefined set of categories or classes, so as to be able to assign the reputation level of the company into different facets, axis or points of view of analysis.</div>
<div><br></div><div>Sentiment analysis is a major technological challenge. The task is so hard that even humans often disagree on the sentiment of a given text. The fact that issues that one individual finds acceptable or relevant may not be the same to others, along with multilingual aspects, cultural factors and different contexts make it very hard to classify a text written in a natural language into a positive or negative sentiment. And the shorter the text is, for example, when analyzing Twitter messages or short comments in Facebook, the harder the task becomes.</div>
<div><br></div><div>On the other hand, text classification techniques, although studied for a longer time, still need more research effort to be able to build complex models with many categories with less workload and increase the precision and recall of the results. In addition, these models should work well with short texts and deal with specific text features that are present in social media messages (such as spelling mistakes, abbreviations, SMS language, etc.).</div>
<div><br></div><div>Within this context, the aim of TASS is to provide a forum for discussion and communication where the latest research work and developments in the field of sentiment analysis in social media, specifically focused on Spanish language, can be shown and discussed by scientific and business communities. The main objective is to promote the application of existing state-of-the-art algorithms and techniques and the design of new ones for the implementation of complex systems able to perform a sentiment analysis and text classification on short text opinions extracted from social media messages (specifically Twitter) published by a series of representative personalities.</div>
<div><br></div><div>The challenge task is intended to provide a benchmark forum for comparing the latest approaches in these fields. In addition, with the creation and release of the fully tagged corpus, we aim to provide a benchmark dataset that enables researchers to compare their algorithms and systems.</div>
<div> </div><div>Four tasks are proposed for the participants covering different aspects of sentiment analysis and automatic text classification.</div><div> </div><div>*** Task 1: Sentiment Analysis at global level ***</div>
<div> </div><div>This task consists on performing an automatic sentiment analysis to determine the global polarity of each message in the test set of the General corpus.</div><div> </div><div>*** Task 2: Topic classification ***</div>
<div><br></div><div>The technological challenge of this task is to build a classifier to automatically identify the topic of each message in the test set of the General corpus.</div><div><br></div><div>*** Task 3: Sentiment Analysis at entity level ***</div>
<div>This task consists on performing an automatic sentiment analysis, similar to Task 1, but determining the polarity at entity level of each message in the Politics corpus.</div><div><br></div><div>In this case, the polarity at entity level included in the training set of the General corpus may be used by participants to train and validate the models.</div>
<div><br></div><div>Task 4: Political tendency identification</div><div>This task moves one step forward and the objective is to estimate the political tendency of each user in the test set of the General corpus, in four possible values: LEFT, RIGHT, CENTRE and UNDEFINED.</div>
<div> </div><div> </div><div>Organizers</div><div> </div><div>==========</div><div> </div><div>Julio Villena-Román Daedalus, Spain</div><div>Janine García-Morera Daedalus, Spain</div>
<div>José Carlos González-Cristóbal<span class="" style="white-space:pre"> </span>Technical University of Madrid, Spain (GSI-UPM)</div><div>L. Alfonso Ureña-López<span class="" style="white-space:pre"> </span>University of Jaén, Spain (SINAI-UJAEN)</div>
<div>Miguel Ángel García-Cumbreras<span class="" style="white-space:pre"> </span>University of Jaén, Spain (SINAI-UJAEN)</div><div>María-Teresa Martín-Valdivia<span class="" style="white-space:pre"> </span>University of Jaén, Spain (SINAI-UJAEN)</div>
<div>Eugenio Martínez-Cámara<span class="" style="white-space:pre"> </span>University of Jaén, Spain (SINAI-UJAEN)</div><div> </div><div>Program Committee (to be confirmed)</div><div><br></div><div>=================</div>
<div><br></div><div>Alexandra Balahur<span class="" style="white-space:pre"> </span>EC-Joint Research Centre, Italy</div><div>José Carlos Cortizo<span class="" style="white-space:pre"> </span>European University of Madrid, Spain</div>
<div>Ana García-Serrano<span class="" style="white-space:pre"> </span>UNED, Spain</div><div>José María Gómez-Hidalgo<span class="" style="white-space:pre"> </span>Optenet, Spain</div><div>Julio Gonzalo-Arroyo<span class="" style="white-space:pre"> </span>UNED, Spain</div>
<div>Carlos A. Iglesias-Fernández<span class="" style="white-space:pre"> </span>Technical University of Madrid, Spain</div><div>Zornitsa Kozareva<span class="" style="white-space:pre"> </span>Information Sciences Institute, USA</div>
<div>Sara Lana-Serrano<span class="" style="white-space:pre"> </span>Technical University of Madrid, Spain</div><div>Bing Liu<span class="" style="white-space:pre"> </span>University of Illinois at Chicago, USA</div>
<div>Paloma Martínez-Fernandez<span class="" style="white-space:pre"> </span>Carlos III University of Madrid, Spain</div><div>Ruslan Mitkov<span class="" style="white-space:pre"> </span>University of Wolverhampton, U.K.</div>
<div>Andrés Montoyo<span class="" style="white-space:pre"> </span>University of Alicante, Spain</div><div>Rafael Muñoz<span class="" style="white-space:pre"> </span>University of Alicante, Spain</div><div>Günter Neumann<span class="" style="white-space:pre"> </span>DFKI, Germany</div>
<div>Paolo Rosso<span class="" style="white-space:pre"> </span>Technical University of Valencia, Spain</div><div>Maite Taboada<span class="" style="white-space:pre"> </span>Simon Fraser University, Canada</div>
<div>
Mike Thelwall<span class="" style="white-space:pre"> </span>University of Wolverhampton, U.K.</div><div>José Antonio Troyano<span class="" style="white-space:pre"> </span>University of Seville, Spain</div><div> </div>
<div> </div><div>Important Dates</div><div> </div><div>=================</div><div> </div><div>June 1st, 2013:<span class="" style="white-space:pre"> </span>Release of training and validation corpora.</div><div>June 15th, 2013:<span class="" style="white-space:pre"> </span>Release of test corpus.</div>
<div>July 1st, 2013:<span class="" style="white-space:pre"> </span>Deadline for registration for the tasks.</div><div>July 15th, 2013:<span class="" style="white-space:pre"> </span>Experiment submissions by participants.</div>
<div>August 2sd, 2013:<span class="" style="white-space:pre"> </span>Evaluation results.</div><div>August 28th, 2013:<span class="" style="white-space:pre"> </span>Submission of papers.</div><div>September 20th, 2013:<span class="" style="white-space:pre"> </span>Workshop.</div>
<div> </div><div> </div><div>Contact Address</div><div> </div><div>===============</div><div> </div><div><a href="mailto:tass@daedalux.es">tass@daedalux.es</a></div><div> </div><div><a href="http://www.daedalus.es/TASS/contact.php">http://www.daedalus.es/TASS/contact.php</a></div>
<div> </div><div> </div><div>===============</div><div><div><br></div>Eugenio Martínez Cámara.<div>Grupo de Investigación <a href="http://sinai.ujaen.es" target="_blank">SINAI</a> / Research Group <a href="http://sinai.ujaen.es" target="_blank">SINAI</a>.<br>
<div>Departamento de Informática / Computer Science Department.<br><div>Universidad de Jaén / University of Jaén.</div><div>emcamara at ujaen dot es<br><br></div></div></div></div>
</div>