SemEval-2016 Task 4: Sentiment Analysis in Twitter

By Preslav Nakov, Alan Ritter, Sara Rosenthal, Fabrizio Sebastiani, Veselin Stoyanov. International Workshop on Semantic Evaluation, 2016

341 citations recorded by the source corpus.

This paper discusses the fourth year of the ”Sentiment Analysis in Twitter Task”. SemEval-2016 Task 4 comprises five subtasks, three of which represent a significant departure from previous editions. The first two subtasks are reruns from prior years and ask to predict the overall sentiment, and the sentiment towards a topic in a tweet. The three new subtasks focus on two variants of the basic “sentiment classification in Twitter” task. The first variant adopts a five-point scale, which confers an ordinal character to the classification task. The second variant focuses on the correct estimation of the prevalence of each class of interest, a task which has been called quantification in the supervised learning literature. The task continues to be very popular, attracting a total of 43 teams.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/846243cb26202b827d9926201ffaaa4cee65b5ae

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

Citations in the corpus

A survey of multimodal sentiment analysis (2017, methodology): “In the latest edition at the time of writing [48], a tool called SwissCheese [49] achieved the best results to date by training convolutional neural networks with large datasets of Tweets with emoticons.”
Stance Detection on Social Media: State of the Art and Trends (2020, background): “…work on SemEval sentiment tasks SemEval-/(2015, 2016, 2017 and 2020), where 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].”
Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction (2019, methodology): “While in 2015 we used macro-averaged F 1 as an ofﬁcial evaluation measure, this year we adopted macro-averaged recall , which was also recently adopted by some other competitions, e.g., by SemEval-2016 Task 4 (Nakov et al., 2016).”
Word Embeddings in Sentiment Analysis (2018, methodology): “In 2017 edition (Rosenthal et al., 2017), machine learning methods were very popular, especially support vector machines and deep neural networks like convolutional neural networks and long short-term neural networks.”
A Survey on Deep Learning (2018, methodology): “Due to the fact that deep learning has shown promising performance on visual data and NLP, different deep learning approaches have been adopted for social network analysis, including semantic evaluation [116, 161, 179], link prediction [99, 163], and crisis response [120].”
COVID-Twitter-BERT: A natural language processing model to analyse COVID-19 content on Twitter (2020, background): “Twitter sentiment SemEval (SE) This is an open dataset from SemEval-2016 Task 4: Sentiment Analysis in Twitter (Nakov et al., 2019).”
SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis (2020, methodology): “Model Year SST Dataset [53] STS Dataset [50] SemEval-2013 [40] SemEval-2015 [47] SemEval-2016 [39] Sanders [2]”
Semeval-2016 Task 4 : Sentiment Analysis in Twitter (2016, methodology): “This project elaborates on two experiments carried out to analyze the sentiment of Tweets, namely, Subtask A and Subtask B from SemEval-2016 Task 4 (Nakov et al., 2016).”
Interpretation of Semantic Tweet Representations (2017, methodology): “Specifically, we evaluate the models for five applications: (1) predict whether the sentiment of tweet is positive, negative or neutral (SA) [26], (2) predict the entity the tweet belongs to (EI) [27], (3) predict the priority of the topic the tweet belongs to (TP) [27], 2017 IEEE/ACM International ”
Affect-LM: A Neural Language Model for Customizable Affective Text Generation (2017, background): “Within this context the analysis of human affect from text is an important topic in natural language understanding, examples of which include sentiment analysis from Twitter (Nakov et al., 2016), affect analysis from poetry (Kao and Jurafsky, 2012) and studies of correlation between function words a”