Google Group: https://groups.google.com/
Evaluation period: January 9-30, 2017
Paper submission: Feb 27,2017
This will be a rerun of SemEval-2016 Task 4 with several changes:
— new subtasks: another language (Arabic) and user information
— new evaluation measures
— new training datasets
— new test datasets
*Subtask A. (rerun): Message Polarity Classification:* Given a message,
classify whether the message is of positive, negative, or neutral sentiment.
*Subtasks B-C. (rerun): Topic-Based Message Polarity Classification:*
Given a message and a topic, classify the message on
B) two-point scale: positive or negative sentiment towards that topic
C) five-point scale: sentiment conveyed by that tweet towards the topic on
a five-point scale.
*Subtasks D-E. (rerun): Tweet quantification:*
Given a set of tweets about a given topic, estimate the distribution of the
D) two-point scale: the ?Positive? and ?Negative? classes
E) five-point scale: the five classes of a five-point scale.
*I. (new)* Polarity classification in another language: In addition to
performing subtasks A-E in English, we will also perform multilingual
experiments by providing a run of these tasks using a test set containing
tweets in Arabic.
*II. (new)* User Information: We aim to harness the user profile
information provided in Twitter such as demographics (e.g., age, location)
as well as the social network. We would like to analyze its impact on
improving sentiment analysis.
*Visit the task website: http://alt.qcri.org/
*Do not miss the important dates:
-Evaluation starts: Mon 09 Jan 2017
-Evaluation ends: Mon 30 Jan 2017
-Results posted: Mon 06 Feb 2017
-Paper submissions due: Mon 27 Feb 2017
-Author notifications: Mon 03 Apr 2017
-Camera ready submissions due: Mon 17 Apr 2017
Sara Rosenthal, IBM Research
Noura Farra, Columbia University
Preslav Nakov, Qatar Computing Research Institute, HBKU