posted by user: grupocole || 2196 views || tracked by 7 users: [display]

TASS 2015 : SEPLN 2015 workshop on: Sentiment Analysis at SEPLN

FacebookTwitterLinkedInGoogle

Link: http://www.daedalus.es/TASS
 
When Sep 15, 2014 - Sep 15, 2014
Where Alicante, Spain
Submission Deadline Jun 10, 2015
Notification Due Jun 25, 2015
Final Version Due Jul 15, 2015
Categories    NLP   text mining
 

Call For Papers

SEPLN 2015 workshop on:
Sentiment Analysis at SEPLN
(TASS 2015)

Sep 15th, 2014
Alicante, Spain

http://www.daedalus.es/TASS

Registration: http://www.daedalus.es/TASS2015/tass2015.php#contact


TASS is an experimental evaluation workshop for sentiment analysis and
online reputation analysis focused on Spanish language, organized as a
satellite event of the annual SEPLN Conference. After three successful
editions in 2012, 2013 and 2014, TASS 2015 will be held on September 15th,
2015 at University of Alicante, Spain.

The aim of TASS is to provide a forum for the 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. These complex
sentiment analysis and text classification systems will work with short text
opinions extracted from social media messages (specifically Twitter).

Several challenge tasks are proposed with the aim of providing 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.

Two tasks are proposed to the participants covering two different levels
of analyses.


*** Task 1: Sentiment Analysis at global level ***

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. This task is a reedition of the task in the previous
years. Participants will be provided with the training set of the General
corpus so that they may train and validate their models.

There will be two different evaluations: one based on 6 different polarity
labels (P+, P, NEU, N, N+, NONE) and another based on just 4 labels (P, N,
NEU, NONE).

Participants are expected to submit (up to 3) experiments for the 6-labels
evaluation, but are also allowed to submit (up to 3) specific experiments
for the 4-labels scenario.

Accuracy (correct tweets according to the gold standard) will be used for
ranking the systems. Precision, recall and F1-measure will be used to
evaluate each individual category.

*** Task 2: Aspect-based sentiment analysis ***

Participants will be provided with a corpus tagged with a series of aspects,
and systems must identify the polarity at the aspect-level. Training and
test sets for two corpora will be provided: the Social-TV corpus, used last
year, and the new Politics corpus, collected this year (both described
later).


Organizers
------------------------
Julio Villena-Rom�n - Daedalus, Spain
Janine Garc�a-Morera - Daedalus, Spain
L. Alfonso Ure�a-L�pez University of Ja�n, Spain (SINAI-UJAEN)
Miguel �ngel Garc�a-Cumbreras - University of Ja�n, Spain (SINAI-UJAEN)
Mar�a-Teresa Mart�n-Valdivia - University of Ja�n, Spain (SINAI-UJAEN)
Eugenio Mart�nez-Cámara - University of Ja�n, Spain (SINAI-UJAEN)


Contributors
---------------------------
David Vilares Calvo - University of Coru�a, Spain
Ferran Pla Santamaria - Polytechnic University of Valencia, Spain
Llu�s F. Hurtado - Polytechnic University of Valencia, Spain
David Tom�s - University of Alicante, Spain
Manuel Montes - National Institute For Astrophysics, Optics and Electronics
(INAOE), Mexico
Luis Villase�or National - Institute For Astrophysics, Optics and
Electronics, Mexico


Program Committee (to be confirmed)
-------------------------------------------------------------------
Jos� Carlos Gonz�lez-Crist�bal Technical University of Madrid, Spain
(GSI-UPM)
Alexandra Balahur EC-Joint Research Centre, Italy
Jos� Carlos Cortizo European University of Madrid, Spain
Ana Garc�a-Serrano UNED, Spain
Jos� Mar�a G�mez-Hidalgo Optenet, Spain
Carlos A. Iglesias-Fern�ndez Technical University of Madrid, Spain
Zornitsa Kozareva Information Sciences Institute, USA
Sara Lana-Serrano Technical University of Madrid, Spain
Paloma Mart�nez-Fernandez Carlos III University of Madrid, Spain
Ruslan Mitkov University of Wolverhampton, U.K.
Andr�s Montoyo University of Alicante, Spain
Rafael Mu�oz University of Alicante, Spain
Constantine Orasan University of Wolverhampton, U.K.S
Mike Thelwall University of Wolverhampton, U.K.
Jos� Antonio Troyano University of Seville, Spain
Jos� M. Perea Ortega University of Extremadura, Spain


Important Dates
--------------------------------
April 6th, 2015: Release of tasks and General corpus.
End of April, 2015: Release of training and test corpora (General,
Social-TV and Politics).
June 10th, 2015: Experiment submissions by participants.
June 25th, 2015: Evaluation results.
July 5th, 2015: Submission of papers.
September 15th, 2015: Workshop.


Contact Address
--------------------------------
tass@daedalus.es
http://www.daedalus.es/T2015/tass2015.php#contact

Related Resources

CAIP 2017   Computer Analysis of Images and Patterns
ACL 2017   The 55th annual meeting of the Association for Computational Linguistics
ISSTA 2017   International Symposium on Software Testing and Analysis
NLDB 2017   22nd International Conference on Natural Language & Information Systems
ASC 2017   The International Workshop on Affective and Sentimental Computing
EMNLP 2017   Conference on Empirical Methods in Natural Language Processing
MIUA 2017   Medical Image Understanding and Analysis
LTA 2017   2nd International Workshop on Language Technologies and Applications
ICCDA 2017   2017 International Conference on Compute and Data Analysis (ICCDA 2017)—SCOPUS & Ei Compendex
EMNLP 2017   Empirical Methods in Natural Language Processing