Automatic Emotion Identification in Twitter (original) (raw)
Related papers
Harnessing Twitter ‘Big Data’for Automatic Emotion Identification
Abstract—User generated content on Twitter (produced at an enormous rate of 340 million tweets per day) provides a rich source for gleaning people's emotions, which is necessary for deeper understanding of people's behaviors and actions. Extant studies on emotion identification lack comprehensive coverage of “emotional situations” because they use relatively small training datasets.
EMOTEX: Detecting Emotions in Twitter Messages
Social media and microblog tools are increasingly used by individuals to express their feelings and opinions in the form of short text messages. Detecting emotions in text has a wide range of applications including identifying anxiety or depression of individuals and measuring well-being or public mood of a community. In this paper, we propose a new approach for automatically classifying text messages of individuals to infer their emotional states. To model emotional states, we utilize the well-established Circumplex model that characterizes affective experience along two dimensions: valence and arousal. We select Twitter messages as input data set, as they provide a very large, diverse and freely available ensemble of emotions. Using hash-tags as labels, our methodology trains supervised classifiers to detect multiple classes of emotion on potentially huge data sets with no manual effort. We investigate the utility of several features for emotion detection, including unigrams, emoticons, negations and punctuations. To tackle the problem of sparse and high dimensional feature vectors of messages, we utilize a lexicon of emotions. We have compared the accuracy of several machine learning algorithms, including SVM, KNN, Decision Tree, and Naive Bayes for classifying Twitter messages. Our technique has an accuracy of over 90%, while demonstrating robustness across learning algorithms.
Emotion Detection using Social Media Data
IJRASET, 2021
Previous research on emotion recognition of Twitter users centered on the use of lexicons and basic classifiers on pack of words models, despite the recent accomplishments of deep learning in many disciplines of natural language processing. The study's main question is if deep learning can help them improve their performance. Because of the scant contextual information that most posts offer, emotion analysis is still difficult. The suggested method can capture more emotion sematic than existing models by projecting emoticons and words into emoticon space, which improves the performance of emotion analysis. In a microblog setting, this aids in the detection of subjectivity, polarity, and emotion. It accomplishes this by utilizing hash tags to create three large emotion-labeled data sets that can be compared to various emotional orders. Then compare the results of a few words and character-based repetitive and convolutional neural networks to the results of a pack of words and latent semantic indexing models. Furthermore, the specifics examine the transferability of the most recent hidden state representations across distinct emotional classes and whether it is possible to construct a unified model for predicting each of them using a common representation. It's been shown that repetitive neural systems, especially character-based ones, outperform pack-of-words and latent semantic indexing models. The semantics of the token must be considered while classifying the tweet emotion. The semantics of the tokens recorded in the hash map may be simply searched. Despite these models' low exchange capacities, the recently presented training heuristic produces a unity model with execution comparable to the three solo models.
IJERT-Using Hashtags to Capture Fine Emotion Categories from Tweets
International Journal of Engineering Research and Technology (IJERT), 2019
https://www.ijert.org/using-hashtags-to-capture-fine-emotion-categories-from-tweets https://www.ijert.org/research/using-hashtags-to-capture-fine-emotion-categories-from-tweets-IJERTCONV7IS01051.pdf Despite recent successes of deep learning in many fields of natural language processing, previous studies of emotion recognition on Twitter mainly focused on the use of lexicons and simple classifiers on bag-of-words models. The central question of our study is whether we can improve their performance using deep learning. To this end, we exploit hashtags to create three large emotion-labelled data sets corresponding to different classifications of emotions. We then compare the performance of several word and character-based recurrent and convolutional neural networks with the performance on bag-of-words and latent semantic indexing models. We also investigate the transferability of the final hidden state representations between different classifications of emotions, and whether it is possible to build a unison model for predicting all of them using a shared representation. We show that recurrent neural networks, especially character-based ones, can improve over bag-of-words and latent semantic indexing models. Although the transfer capabilities of these models are poor, the newly proposed training heuristic produces a unison model with performance comparable to that of the three single models.
Using hashtags to capture fine emotion categories from tweets
2014
Detecting emotions in microblogs and social media posts has applications for industry, health, and security. Statistical, supervised automatic methods for emotion detection rely on text that is labeled for emotions, but such data is rare and available for only a handful of basic emotions. In this paper, we show that emotion-word hashtags are good manual labels of emotions in tweets. We also propose a method to generate a large lexicon of word-emotion associations from this emotionlabeled tweet corpus. This is the first lexicon with real-valued word-emotion association scores. We begin with experiments for six basic emotions and show that the hashtag annotations are consistent and match with the annotations of trained judges. We also show how the extracted tweets corpus and word-emotion associations can be used to improve emotion classification accuracy in a different non-tweets domain. Eminent psychologist, Robert Plutchik, had proposed that emotions have a relationship with personality traits. However, empirical experiments to establish this relationship have been stymied by the lack of comprehensive emotion resources. Since personality may be associated with any of the hundreds of emotions, and since our hashtag approach scales easily to a large number of emotions, we extend our corpus by collecting tweets with hashtags pertaining to 585 fine emotions. Then, for the first time, we present experiments to show that fine emotion categories such as that of excitement, guilt, yearning, and admiration are useful in automatically detecting personality from text. Stream-of-consciousness essays and collections of Facebook posts marked with personality traits of the author are used as the test sets.
Affective analysis of text in tweets
2018
Affective computing is the study and development of devices that can recognize emotions through various modes such as video, audio and text automatically. In this thesis, I focus on the problem of affective computing in short texts, in particular, tweets. With the evolution of social media in the recent years, there has been a rapid growth of interactions that take occur online, which are expressive in terms of emotion. Internet users today have several diverse methods of being expressive through text, such as by using abbreviations, emoticons and hashtags. I use traditional lexical features and word embeddings to extract semantic and lexical information from the input text. I develop models ranging from linear and tree-based models to deep neural networks to perform emotion detection on Tweets. I create an ensemble of these methods to make my final predictions. I evaluate the ensemble on the SemEval 2018 dataset containing intensity and class annotations for emotions in tweets. I finally perform an error analysis of these algorithms and highlight potential areas of improvement.
Real-Time Emotion Recognition of Twitter Posts Using a Hybrid Approach
2020
The analysis of social media posts is a challenging task, particularly the recognition of user emotions. Text is one of the most common mediums used by humans to express emotion, particularly on social media platforms. As emotions play a pivotal role in human interaction, the ability to recognize them by analyzing textual content has various applications in human-computer interaction (HCI) and natural language processing (NLP). Previous studies on emotion classification used bag-of-words classifiers or deep learning on static Twitter data. Our proposed model is a hybrid approach that uses a combination of keyword-based and learning-based models to perform textual emotion recognition on Twitter posts obtained in real-time. Textual feature extraction is carried out by standard Natural Language Processing (NLP) techniques such as Part-of-Speech (PoS) tagging and topic modeling along with classification done using the random forest algorithm. Results show that our proposed model perform...
joint conference on lexical and computational semantics, 2012
Detecting emotions in microblogs and social media posts has applications for industry, health, and security. However, there exists no microblog corpus with instances labeled for emotions for developing supervised systems. In this paper, we describe how we created such a corpus from Twitter posts using emotionword hashtags. We conduct experiments to show that the self-labeled hashtag annotations are consistent and match with the annotations of trained judges. We also show how the Twitter emotion corpus can be used to improve emotion classification accuracy in a different domain. Finally, we extract a word-emotion association lexicon from this Twitter corpus, and show that it leads to significantly better results than the manually crafted WordNet Affect lexicon in an emotion classification task. 1
2014
Twitter is a social media application, which can give a sign for identifying user emotion. Identification of user emotion can be utilized in commercial domain, health, politic, and security problems. The problem of emotion identification in twit is the unstructured short text messages which lead the difficulty to figure out main features. In this paper, we propose a new framework for identifying the tendency of user emotions using specific features, i.e. hashtag, emoji, emoticon, and adjective term. Preprocessing is applied in the first phase, and then user emotions are identified by means of classification method using kNN. The proposed method can achieve good results, near ground truth, with accuracy of 92%.
Emotion and Sentiment Analysis from Twitter Text
Journal of Computational Science, 2019
Online social networks have emerged as new platform that provide people an arena to share their views and perspectives on different issues and subjects with their friends, family, and other users. We can share our thoughts, mental states, moments and stances on specific social, and political issues through texts, photos, audio/video messages and posts. Indeed, despite the availability of other forms of communication, text is still one of the most common ways of communication in a social network. Twitter was chosen in this research for data collection, experimentation and analysis. The research described in this thesis is to detect and analyze both sentiment and emotion expressed by people through texts in their Twitter posts. Tweets and replies on few recent topics were collected and a dataset was created with text, user, emotion and sentiment information. The customized dataset had user detail like user ID, user name, user's screen name, location, number of tweets/followers/likes/followees. Similarly, for textual information, tweet ID, tweet time, number of likes/replies/retweets, tweet text, reply text and few other text based data were collected. The texts of the dataset were then annotated with proper emotions and sentiments according to some benchmark models. The customized dataset was then used to detect sentiment and emotion from tweets and their replies using machine learning. The influence scores of users were also calculated based on various user-based and tweet-based parameters. Based on those information, both generalized and personalized recommendations were offered for users based on their Twitter activities.