W3C home > Mailing lists > Public > public-sentiment@w3.org > February 2017

Call for participation: Stance and Gender Detection in Tweets on Catalan Independence" at IBEREVAL17

From: Viviana Patti <patti@di.unito.it>
Date: Fri, 24 Feb 2017 09:25:44 +0100
To: public-sentiment@w3.org
Message-ID: <2b21ba6d-de28-d574-d14c-c44de3c7ece2@di.unito.it>
[Apologies for multiple postings]

----------------------------------------------
First Call for Participation
----------------------------------------------

IBEREVAL 2017:

Task: Stance and Gender Detection in Tweets on Catalan Independence

Webpage: http://stel.ub.edu/Stance-IberEval2017

held in conjunction with the SEPLN 2017 International conference
19th September 2017, University of Murcia, Murcia (Spain)

----------------------------------------------

The aim of this task is to detect the author’s gender and stance (i.e., 
the position adopted in favor, against or neutral with respect to an 
issue) in tweets written in Spanish and/or Catalan on the subject of the 
independence of Catalonia. Stance detection is related to sentiment 
analysis, but there are some significant differences:
In sentiment analysis, the systems detect whether a sentiment 
(especially, an opinion) is positive, negative or neutral.
In stance detection, the systems detect whether the author is favorable 
or unfavorable to a given issue, which may or may not be explicitly 
mentioned in the text.
In this task, the issue or target is a political one, the independence 
of Catalonia. Stance detection is particularly interesting for studying 
political debates in which the topic is controversial. Therefore for 
this task we have chosen to focus on a specific political target: the 
independence of Catalonia. This task is also related to a textual 
inference task due to the fact that the position of the tweeter is often 
expressed implicitly, therefore, the stance has to be inferred in many 
cases.

In the training phase, the participants will be provided with the 
TW-CaSe training corpus manually annotated with stance and gender. The 
possible stance labels are: ‘favor’, ‘against’ and ‘none’ for the 
stance, and ‘male’ and ‘female’ for gender. Later, the unlabelled test 
data will be released. After the assessment, the labels for the test 
data will also be released.

We cordially invite all researchers and practitioners from all fields to 
participate in this task: Stance and Gender detection in tweets on 
Catalan Independence.
We also invite the participants to subscribe to our mailing list in 
order to be kept up to date with the latest news related to the task: 
stance-ibereval2017@googlegroups.com

----------------------------------------------
Important Dates
----------------------------------------------


20 March 2017: Release of training data (training period starts)
24 April 2017: Release of test data
8 May 2017: Systems results
15 May 2017: Results notification
29 May 2017: Working papers submission
12 June 2017: Working papers reviewed (peer-reviewed)
26 June 2017: Camera ready
19 September 2017: IBEREVAL 2017 Workshop


----------------------------------------------
Track Coordinators
----------------------------------------------

Mariona Taulé, M. Antònia Martí (Universitat de Barcelona (UB), Spain)
Francisco Rangel (Autoritas Consulting, Spain)
Paolo Rosso (Universitat Politècnica de València (UPV), Spain)
Viviana Patti, Cristina Bosco (Università degli Studi di Torino (UniTO), 
Italy)

----------------------------------------------
Contact
----------------------------------------------

E-mail: stancetask2017@gmail.com
Track Web page:  stel.ub.edu/Stance-IberEval2017
Received on Friday, 24 February 2017 08:26:53 UTC

This archive was generated by hypermail 2.3.1 : Friday, 24 February 2017 08:26:53 UTC