SemEval-2015 Task 10: Sentiment Analysis in Twitter

By Sara Rosenthal, Preslav Nakov, Svetlana Kiritchenko, Saif M. Mohammad, Alan Ritter, Veselin Stoyanov. International Workshop on Semantic Evaluation, 2015

426 citations recorded by the source corpus.

In this paper, we describe the 2015 iteration of the SemEval shared task on Sentiment Analysis in Twitter. This was the most popular sentiment analysis shared task to date with more than 40 teams participating in each of the last three years. This year’s shared task competition consisted of five sentiment prediction subtasks. Two were reruns from previous years: (A) sentiment expressed by a phrase in the context of a tweet, and (B) overall sentiment of a tweet. We further included three new subtasks asking to predict (C) the sentiment towards a topic in a single tweet, (D) the overall sentiment towards a topic in a set of tweets, and (E) the degree of prior polarity of a phrase.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/ae47d53a9d712d655f88362bddfae226c651742a

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

SemEval-2016 Task 4: Sentiment Analysis in Twitter (2016, methodology): “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).”
UNITN: Training Deep Convolutional Neural Network for Twitter Sentiment Classification (2015, methodology): “We apply our deep learning model on two sub-tasks of Semeval-2015 Twitter Sentiment Analysis (Task 10) challenge (Rosenthal et al., 2015): phrase-level (subtask A) and message-level (subtask B).”
Challenges in Sentiment Analysis (2017, positive): “(Rosenthal, Nakov, Kiritchenko, Mohammad, Ritter, & Stoyanov, 2015; Rosenthal, Ritter, Nakov, & Stoyanov, 2014b; Mohammad et al., 2016a; Mohammad, Zhu, Kiritchenko, & Martin, 2015b).”
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]”
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora (2016, methodology): “We evaluate our approach using the test set from the 2015 SemEval task 10E competition (Rosenthal et al., 2015), and we use the embeddings constructed by Rothe et al.”
emoji2vec: Learning Emoji Representations from their Description (2016, background): “Concurrently we observe an increased interest in natural language processing on social media data (Ritter et al., 2011; Gattani et al., 2013; Rosenthal et al., 2015).”
SemEval-2016 Task 6: Detecting Stance in Tweets (2016, background): “Past work on stance detection includes that by Somasundaran and Wiebe (2010), Anand et al.”
Word Embeddings in Sentiment Analysis (2018, methodology): “In the 2015 edition (Rosenthal et al., 2015), most participants used machine learning techniques; in many of the subtasks, the top ranking systems used deep learning methods and word embeddings, like the system submitted by Severyn and Moschitti (2015), which was ranked 1st in subtask A and 2nd in s”
Recurrent Dropout without Memory Loss (2016, methodology): “We use Twitter sentiment corpus from SemEval-2015 Task 10 (subtask B) (Rosenthal et al., 2015).”
Learning and Evaluating Emotion Lexicons for 91 Languages (2020, neutral): “More recent approaches focus heavily on word embeddings, either using semi-supervised graph-based approaches (Wang et al., 2016; Hamilton et al., 2016; Sedoc et al., 2017) or fully supervised methods (Rosenthal et al., 2015; Li et al., 2017; Rothe et al., 2016; Du and Zhang, 2016).”
Word Emotion Induction for Multiple Languages as a Deep Multi-Task Learning Problem (2018, background): “SemEval-2015 Task 10E featured polarity induction on Twitter (Rosenthal et al., 2015).”
Like It or Not (2016, background): “SemEval-2015 contains 1899 positive, 1008 negative, and 190 neutral additional tweets [Rosenthal et al. 2015].”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “Our experimental evaluation on a recent benchmark from Semeval-2015 [129] shows that our model ranks 1st on the term-level subtask (among 11 submissions) and 2nd on the message-level subtask (among 40 systems).”
From classification to quantification in tweet sentiment analysis (2016, methodology): “The tweet sentiment classification (TSC) shared task which has taken place in the context of the last three SemEval evaluation campaigns (where it is called “Sentiment Analysis in Twitter” – see [47,53,54]) has been, in all three editions, the SemEval task with the highest number of participants.”