• Corpus ID: 192621558

Power of Predictive Analytics: Using Emotion Classification of Twitter Data for Predicting 2016 US Presidential Elections

@article{Srinivasan2019PowerOP,
  title={Power of Predictive Analytics: Using Emotion Classification of Twitter Data for Predicting 2016 US Presidential Elections},
  author={Satish Mahadevan Srinivasan and Raghvinder S. Sangwan and Colin J. Neill and Tianhai Zu},
  journal={Social media and society},
  year={2019},
  volume={8},
  pages={211-230},
  url={https://api.semanticscholar.org/CorpusID:192621558}
}
The potentiality of a lexicon-based classifier, NRC, which can mine emotions and sentiments in tweets is demonstrated, indicating the potential emotion and sentiment-based classification holds in predicting the outcome of significant social and political events.
thejsms.org
6 Citations
Background Citations
2

Figures and Tables from this paper

6 Citations

A Data-Centric Approach to Understanding the 2020 U.S. Presidential Election

Using the well-known Lexicon-based NRC classifier, nearly seven million tweets across seven battleground states in the U.S. are classified to understand the emotions and sentiments expressed by U.S. citizens toward the 2020 presidential candidates and the swing directions of each battleground state are predicted.

Emotion Analysis from Texts

An overview of research from emotion psychology is provided which sets the ground for choosing adequate NLP methodology, and existing resources and classification methods used for emotion analysis in texts are presented.

Discrete Emotions Detection on Social Media: A Systematic Review and Comparative Analysis

Amid the rapid advancements in social media communication, such findings may provide a foundational exploration for discerning discrete emotions online, paving the way for the development of refined navigational tools in the complex emotional landscape of the digital realm.

Sentiment Analysis of Democratic Presidential Primaries Debate Tweets Using Machine Learning Models

The sentiment analysis of tweets posted during the third Democratic primary debate is focused on to determine whom the Twitter users believe won or lost the debate.

Leveraging twitter data to understand nurses’ emotion dynamics during the COVID-19 pandemic

The results found that the emotional dynamics of registered and student nurses were significantly correlated with the development of COVID-19 at different waves and both groups showed various emotional changes parallel to the scale of pandemic waves and corresponding public health responses.

Mining, Assessing, and Improving Arguments in NLP and the Social Sciences

This tutorial is an updated edition of the EACL 2023 tutorial and will have a strong interdisciplinary and interactive nature, and will be structured along three main coordinates: the notions of argument quality (AQ) across disciplines, and the generation of improved arguments.

32 References

EmpaTweet: Annotating and Detecting Emotions on Twitter

A corpus collected from Twitter with annotated micro-blog posts annotated at the tweet-level with seven emotions: ANGER, DISGUST, FEAR, JOY, LOVE, SADNESS, and SURPRISE is introduced.

Emotion classification of social media posts for estimating people’s reactions to communicated alert messages during crises

A methodology for collecting a large number of relevant tweets and annotating them with emotional labels is described, used for creating a training dataset consisting of manually annotated tweets from the Sandy hurricane and as a basis for constructing a decision support tool.

EMOTEX: Detecting Emotions in Twitter Messages

This paper proposes a new approach for automatically classifying text messages of individuals to infer their emotional states, using hash-tags as labels and utilizes a lexicon of emotions to tackle the problem of sparse and high dimensional feature vectors of messages.

Twitter as a Corpus for Sentiment Analysis and Opinion Mining

This paper shows how to automatically collect a corpus for sentiment analysis and opinion mining purposes and builds a sentiment classifier, that is able to determine positive, negative and neutral sentiments for a document.

Unsupervised sentiment analysis with emotional signals

This work investigates whether the signals in social media can potentially help sentiment analysis by providing a unified way to model two main categories of emotional signals, i.e., emotion indication and emotion correlation and incorporates the signals into an unsupervised learning framework for sentiment analysis.

Sentiment Strength Detection in Short Informal Text 1

A new algorithm is partly filled with a new algorithm, SentiStrength, to extract sentiment strength from informal English text, using new methods to exploit the de-facto grammars and spelling styles of cyberspace.

Twitter as a Corpus for Sentiment Analysis and Opinion Mining

A novel solution to target-oriented sentiment summarization and SA of short informal texts with a main focus on Twitter posts known as “tweets” is introduced and it is shown that the hybrid polarity detection system not only outperforms the unigram state-of-the-art baseline, but also could be an advantage over other methods when used as a part of a sentiment summarization system.

Feeler: Emotion Classification of Text Using Vector Space Model

An emotion enabled video player which automatically detects the emotion from subtitle text of video and displays corresponding emoticon is developed and tested and discussed the results of classification using cross-validation technique for emotion classification and sentiment analyses on both the ISEAR and SemEval datasets.

Robust Sentiment Detection on Twitter from Biased and Noisy Data

In this paper, we propose an approach to automatically detect sentiments on Twitter messages (tweets) that explores some characteristics of how tweets are written and meta-information of the words…

Using a Heterogeneous Dataset for Emotion Analysis in Text

This paper adopts a supervised machine learning approach to recognize six basic emotions using a heterogeneous emotion-annotated dataset which combines news headlines, fairy tales and blogs.