ICT Express · 2020 · 123 citations · 11 references
ComputingComputer ScienceData ScienceComputational LinguisticsMachine LearningNatural Language ProcessingAffective ComputingDeep LearningOpinion MiningSentiment AnalysisSocial MediaText MiningAffective FeaturesEmotion DetectionLexicon-based Sentiment AnalysisSentiment ClassificationSentiment FeaturesText-based Emotion AnalysisTextual Sentiment AnalysisTweet Sentiment Analysis
Emoticons are increasingly used in text to convey feelings, yet prior machine‑learning approaches have treated text and emoticons separately, overlooking the emotional content of combined expressions. This study proposes an algorithm and method for sentiment analysis that jointly considers text and emoticons. The method applies both machine‑learning and deep‑learning classifiers to Twitter airline data, extracting features such as TF‑IDF, bag‑of‑words, n‑grams, and emoticon lexicons, and evaluates text, emoticon, and combined modalities. Results show that emoticons dominate the overall sentiment when present, and deep‑learning models outperform traditional machine‑learning approaches.
People nowadays use emoticons in their text increasingly in order to express their feelings or recapitulate their words. Earlier machine learning techniques only involve the classification of text, emoticons or images solely where emoticons with text have always been neglected, thus ignored lots of emotions. This research proposed an algorithm and method for sentiment analysis using both text and emoticon. In this work, both modes of data were analyzed in combined and separately with both machine learning and deep learning algorithms for finding sentiments from twitter based airline data using several features such as TF–IDF, Bag of words, N-gram, and emoticon lexicons. This research demonstrates that whenever emoticons are used, their associated sentiment dominates the sentiment conveyed by textual data analysis. Also, deep learning algorithms are found to be better than machine learning algorithms.
11
Twitter as a Corpus for Sentiment Analysis and Opinion Mining
2010 · 2.7K citations · Full text
Attention-based LSTM for Aspect-level Sentiment Classification
Yequan Wang, Minlie Huang, Xiaoyan Zhu et al. · 2016 · 2.3K citations · Full text
SemEval-2016 Task 5: Aspect Based Sentiment Analysis
Maria Pontiki, Dimitrios Galanis, Haris Papageorgiou et al. · 2016 · 1.3K citations · Full text
Language Studies, Linguistics, Computational Linguistics +16