[Corpora-List] 1st call for participation -- SardiStance @ EVALITA 2020

Alessandra Teresa Cignarella cigna at di.unito.it
Fri Apr 3 11:26:33 CEST 2020


[Apologies for cross-posting]

************************* Call for Participants *************************

Task: *Stance Detection in Italian Tweets (SardiStance)* in the context of EVALITA 2020 <http://www.evalita.it/2020/> Info: https://di.unito.it/sardistance2020 Final Workshop: co-located with CLiC-it 2020 <http://clic2020.ilc.cnr.it/it/home/> 30th November - 3rd December 2020, Bologna, Italy

Registration is required to obtain data and participate in the shared task. (Please register by subscribing to the google group: https://groups.google.com/d/forum/sardistance-evalita2020)

----------------------------------------------------- The SardiStance Task 🐟 🐟 🐟 -----------------------------------------------------

We invite participants to detect the stance of Italian tweets regarding the target of interest "*Movimento delle Sardine*" and to explore features based on the textual content of the tweet, such as structural, stylistic, and affective features, but also features based on contextual information that documents not emerge directly from the text, such as for instance knowledge about the domain of the political debate or information about the user's community. Overall, we propose two different subtasks:

*Task A - Textual Stance Detection:* The first task is a three-class classification task where the system has to predict whether a tweet is in favour, against or neutral towards the given target, exploiting only textual information, i.e. the text of the tweet.

*Task B - Contextual Stance Detection:* The second task is the same as the first one: a three-class classification task where the system has to predict whether a tweet is in favour, against or neutral towards the given target. Here participants will have access to a wider range of *contextual information based on the post* such as: the number of retweets, the number of favours, the number of replies and the number of quotes received to the tweet, the type of posting source (e.g. iOS or Android), and date of posting. Furthermore we will share (and encourage its exploitation) *contextual information related to the user*, such as: number of tweets ever posted, user's bio, user's number of followers, user's number of friends. Additionally we will share *users' contextual information about their social network*, such as: friends, replies, retweets, and quotes' relations.

Further details on the task, data, and evaluation are available at the task website: https://di.unito.it/sardistance2020 <http://di.unito.it/ironita18>

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

- *29th May 2020*: distribution of training data (on the Task Web Page)

- *4th September 2020*: distribution of test data

- *4th - 24th September 2020*: evaluation window and collection of participants' results.

- *2nd October 2020*: assessment returned to participants

- *6th November **2020*: technical reports due to organizers (camera-ready).

- *2nd or 3rd December 2020*: Final Workshop (co-located with CLiC-it 2020 <http://clic2020.ilc.cnr.it/it/home/>), Bologna, Italy

Further details will be made available in the near future.

---------------- Organizers ----------------

*Mirko Lai ¹ * *Alessandra T. Cignarella ¹ ²* Cristina Bosco ¹ Viviana Patti ¹ Paolo Rosso ²

*1. Università degli Studi di Torino, Italy*

*2. Universitat Politècnica de València, Spain*

------------- Contacts -------------

Join the google group: https://groups.google.com/d/forum/sardistance-evalita2020 And contact the organizers: Mirko Lai (mirko.lai at unito.it) and Alessandra T. Cignarella (cigna at di.unito.it) -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 9682 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20200403/a63129eb/attachment.txt>



More information about the Corpora mailing list