SemEval-2014 Task 9: Sentiment Analysis in Twitter

By Preslav Nakov, Alan Ritter, Sara Rosenthal, Fabrizio Sebastiani, Veselin Stoyanov. International Workshop on Semantic Evaluation, 2014

587 citations recorded by the source corpus.

We describe the Sentiment Analysis in Twitter task, ran as part of SemEval-2014. It is a continuation of the last year’s task that ran successfully as part of SemEval2013. As in 2013, this was the most popular SemEval task; a total of 46 teams contributed 27 submissions for subtask A (21 teams) and 50 submissions for subtask B (44 teams). This year, we introduced three new test sets: (i) regular tweets, (ii) sarcastic tweets, and (iii) LiveJournal sentences. We further tested on (iv) 2013 tweets, and (v) 2013 SMS messages. The highest F1score on (i) was achieved by NRC-Canada at 86.63 for subtask A and by TeamX at 70.96 for subtask B.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/2b74f47b1336c948d2371a30209ec56c936763a9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

SemEval-2018 Task 3: Irony Detection in English Tweets (2018, background): “However, the SemEval-2014 shared task Sentiment Analysis in Twitter (Rosenthal et al., 2014) demonstrated the impact of irony on automatic sentiment classiﬁcation by including a test set of ironic tweets.”
Stance Detection on Social Media: State of the Art and Trends (2020, background): “here the aim of sentiment analysis task is to determine the polarity towards an aspect of a product such as cell phone [Patwa et al. 2020; Pontiki et al. 2015; Nakov et al. 2016; Pontiki et al. 2016; Rosenthal et al. 2017]. Unlike sentiment analysis, stance detection mainly focus on identifying a pe”
SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News (2017, background): “A series of tasks have concentrated on Sentiment Analysis in Twitter (Nakov et al., 2013; Rosenthal et al., 2014; Rosenthal and Stoyanov, 2015).”
Do Convolutional Networks need to be Deep for Text Classification ? (2017, methodology): “The SemEval challenge has been setup in 2013 to boost this field and is still bringing together many competitors who have been using an increasing proportion of deep learning models over the years (Nakov et al. 2013; Rosenthal et al. 2014; Nakov et al. 2016).”
How Translation Alters Sentiment (2016, methodology): “As the English corpus, we choose the SemEval-2013 Task 2 (Sentiment Analysis in Twitter) training dataset (Wilson et al., 2013) for our experiments because just as the BBN dataset, this is a dataset of social media posts.”
Code Mixing: A Challenge for Language Identification in the Language of Social Media (2014, methodology): “SEMEVAL 2013 Twitter Corpus (SemevalTwitter): To cope with the language of social media we use the SEMEVAL 2013 (Nakov et al., 2013) training data for the Twitter sentiment analysis task.”
SemEval-2016 Task 4: Sentiment Analysis in Twitter (2016, background): “As a testament to the prominence of research on sentiment analysis in Twitter, the tweet sentiment classiﬁcation (TSC) task has attracted the highest number of participants in the last three SemEval campaigns (Nakov et al., 2013; Rosenthal et al., 2014; Rosenthal et al., 2015; Nakov et al., 2016b).”
Global Belief Recursive Neural Networks (2014, methodology): “The main dataset is provided by the SemEval 2013, Task 2 competition [18].”
SemEval-2017 Task 4: Sentiment Analysis in Twitter (2017, methodology): “The English training and development data this year consisted of the data from all previous editions of this task (Nakov et al., 2013; Rosenthal et al., 2014, 2015; Nakov et al., 2016b).”
From classification to quantification in tweet sentiment analysis (2016, background): “The SemEval2013, SemEval2014, SemEval2015, and SemE-val2016 datasets are described more in detail in Nakov et al. (2013), Rosenthal et al. (2014, 2015), and Nakov et al. (2016), respectively, while all of the other datasets (Sanders, SST, OMD, HCR, GASP, WA, WB) are described in detail in Saif et…”
A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks (2016, methodology): “In particular, we use Semeval 2014 (Rosenthal et al., 2014) Twitter Sentiment Analysis Dataset for the training.”
Sentiment Embeddings with Applications to Sentiment Analysis (2016, methodology): “On SemEval dataset, we follow the experimental protocols officially provided by SemEval 2014 [68].”
Like It or Not (2016, methodology): “A similar annotation process followed the SemEval-2013 [Rosenthal et al. 2014] process.”