[Corpora-List] SemEval-2017 Task 5 : Fine-Grained Sentiment Analysis on Financial Microblogs and News

André Freitas andrenfreitas at gmail.com
Wed Jan 11 23:29:47 CET 2017


* SemEval-2017 Task 5 * = Fine-Grained Sentiment Analysis on Financial Microblogs and News =

Call for participation.

The evaluation period started!

website: http://alt.qcri.org/semeval2017/task5/

Sentiments and opinions expressed on social media and news can strongly affect market dynamics. Sentiment analysis over the financial domain depends on particular computational linguistics challenges such as the modelling of finance-specific lexicon, interpretation of economic and financial events, use of financial background knowledge, on the top of usual challenges for sentiment analysis such as sarcasm/irony detection, lack of context and poorly structured language.

Research effort is required to overcome and address these issues. This Semeval task aims at catalyzing discussions around approaches of semantic interpretation of financial texts by targeting a financial sentiment analysis task, which identifies bullish (optimistic; believing that the stock price will increase) and bearish (pessimistic; believing that the stock price will decline) sentiment associated with companies and stocks.

*The Task:*

Participating systems will need to address the following task: given a text instance (microblog message in Track 1, news statement or headline in Track 2), predict the sentiment score for each of the companies/stocks mentioned. Sentiment values need to be floating point values in the range of -1 (very negative/bearish) to 1 (very positive/bullish), with 0 designating neutral sentiment.

Track 1 - Microblog Messages

* StockTwits Messages: Consists of microblog messages focusing on stock market events and assessments from investors and traders, exchanged via the StockTwits microblogging platform. Typical stocktwits consist of references to company stock symbols (so-called cashtags - a stock symbol preceded by “$”, e.g. “$AAPL” for the company Apple Inc.), a short supporting text and references links.

* Twitter Messages: Twitter posts containing company stock symbols (cashtags), in the same style as the StockTwits messages.

Example: 'Este Lauder beats on Revenues and EPS and boosts dividend 25% - global growth in the Middle Class trend continues. $EL $NKE $SBUX $AAPL'

Track 2 - News

News headlines from financial sources such as Bloomberg, Reuters, Financial Times, Wall Street Journal.

Example: 'First Solar, Vivint Solar Lead Short Interest Trend'

The test collection contains the companies/cashtags which are referenced in the text, the text spans associated to each company (for microblogs) and the associated sentiment scores.

*Important Dates:*

11 Jan 2017: Evaluation starts 30 Jan 2017: Evaluation ends 06 Feb 2017: Results posted 27 Feb 2017: Paper submissions due 03 Apr 2017: Author notifications 17 Apr 2017: Camera ready submissions due

Questions and comments: semeval-2017-task-5 at googlegroups.com Registration for the task: http://bit.ly/2b9fb7o -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3640 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20170111/9533f994/attachment.txt>



More information about the Corpora mailing list