A System for Real-time Twitter Sentiment Analysis of 2012 U.S. Presidential Election Cycle
By Dogan Can, Ebrahim (Abe) Kazemzadeh, F. Bar, Shrikanth S. Narayanan. 2012
677 citations recorded by the source corpus.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Richard Socher
- Christopher D. Manning
- Samuel R. Bowman
- Noah A. Smith
- Mohit Bansal
- Christopher Potts
- Caiming Xiong
- Luke S. Zettlemoyer
Citations in the corpus
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, background): “While there are several datasets with document and chunk labels available, there is a need to better capture sentiment from short comments, such as Twitter data, which provide less overall signal per document.”
- Sentiment analysis using deep learning architectures: a review (2019, methodology): “Xiong et al. (2018b) developed a model called Multi-level Sentiment-enriched Word Embedding (MSWE), which uses a Multi-layer perceptron (MLP) to model word-level sentiment information and CNN to model tweetlevel sentiment information.”
- Predicting political preference of Twitter users (2013, methodology): “Supervised methods, on the other hand, train prediction models either on manually labeled tweets [3], [16] or on tweets with an emotional context [9], i.”
- Text Mining in Big Data Analytics (2020, background): “presidential election [181], (c) the effects of Twitter on brand management [182]”
- Recursive deep learning for natural language processing and computer vision (2014, background): “For the more difficult multiclass case including a neutral class, accuracy is often below 60% for short messages on Twitter (Wang et al., 2012).”
- Tampering with Twitter’s Sample API (2018, background): “[67] presented a system for real-time Twitter analysis of the 2012 US Presidential Elections.”
- The Operational Value of Social Media Information (2018, background): “In fact, past literature has shown that bag-of-words classifiers with three levels of sentiment (i.e. positive, negative and neutral) often are below 60% accurate (Wang et al. 2012).”