Emotion Detection on Twitter Data using Knowledge Base Approach (original) (raw)

Two Step Approach for Emotion Detection on Twitter Data

International Journal of Computer Applications

Emotional states of individuals, also known as moods, are central to the expression of thoughts, ideas and opinions, and in turn impact attitudes and behavior". In this paper we have proposed a method which detects the emotion or mood of the tweet and classify the twitter message under appropriate emotional category. Our approach is a two-step approach, it is so called as it uses two approaches for the classification process, one is Rule Based approach and the other is Machine Learning approach. The first approach is the Rule Based Approach (RBA), our minor contributions in this approach are pre-processing, tagging, feature selection and Knowledge base creation. Feature selection is based on tags. Our second approach is Machine Learning Approach (MLA), in this the classifier is based on supervised machine learning algorithm called Naïve Bayes which requires labeled data. Naïve Bayes is used to detect and classify the emotion of a tweet. The output of RBA is given to MLA as input because MLA requires labeled data which we have already created through RBA. We have compared the accuracies of both the approaches, observed that, with the rule based approach we are able to classify the tweets with accuracy around 85% and with the machine learning approach the

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.

Emotion Categorization Using Twitter

International Journal of Advanced Trends in Computer Science and Engineering, 2020

Recent interactions between regular users of net can be seen using Micro blogging. Several users share their views on various aspects of life regularly. The micro blogging webs resources are wealthy sources of information for opinion mining as well as sentiment analysis. As a result of micro blogging has appeared comparatively recently, there are some analysis works that were dedicated to this subject. Using sentiments present in twwts posted by users, organizations can get a quick check non public opinion about their business and about their whole organization structure. Sentiment classifiers for twitter datasets are worked upon in recent times and has observed a variety of results. Sentiment classification will benefit corporations by providing knowledge for analyzing client feedback for product or conducting research. Sentiment classifiers ought to be ready to handle tweets in multiple languages[9] to hide a bigger portion of the obtainable tweets. In this paper we have developed a sentiment classifier which can tell positive, negative and neutral sentiment for a tweet. Experimental evaluations show that our projected techniques are efficient and perform higher than techniques found in literature. We here propose to mine sentiments from micro blogging service, Twitter, where users blog for real time situations. They express their opinions for almost every domain. Throughout this paper, we present a hybrid approach for exploitation lexicon based technique to find out the language point of direction of the opinion words in tweets.

Multi-class twitter emotion classification: A new approach

International Journal of …, 2012

Micro blogging today has become a very popular communication tool among Internet users. Millions of users share opinions on different aspects of life every day. Therefore micro blogging web-sites are rich sources of data for opinion mining and sentiment analysis. Because micro blogging has appeared relatively recently, there are a few research works that are devoted to this topic. In this paper, we are focusing on using Twitter, the most popular micro blogging platform, for the task of Emotion analysis. We will show how to automatically collect a corpus for Emotion analysis and opinion mining purposes and then perform linguistic analysis of the collected corpus and explain discovered phenomena. Using the corpus, we will build a Emotion classifier that will be able to determine the emotion class of the person writing.

Emotion Analysis of Twitter using Opinion Mining

With the rise in use of micro-blogging sites like Twitter, people are able to express and share their opinions with each other on a common platform. Currently all work in opinion mining research has quantified & assessed the expression of opinion as positive, negative or neutral values, we intend to categorize the opinion on the basis of five emotions, namely Happiness, Anger, Fear, Sadness & Disgust, which have been globally accepted & defined in human psychology. This paper presents a method to assess these identified types of emotions in a tweet using opinion mining. A two-step approach is proposed, where firstly, to identify the sentiment; we extract the opinion words (a combination of the adjectives along with the verbs and adverbs) in the tweets and subsequently use a novel algorithm to find the emotion values of opinion words. The initial results show that it is a motivating technique, which may find potential applications in business intelligence, government policy making, amongst others.

Automatic Emotion Identification in Twitter

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. To overcome this bottleneck, we have automatically created a large emotion-labeled dataset (of about 3,700 tweets) by harnessing emotion-related hashtags available in the tweets. We have applied two different machine learning algorithms for emotion identification, to study the effectiveness of various feature combinations as well as the effect of the size of the training data on the emotion identification task. Our experiments demonstrate that a combination of unigrams, bigrams, sentiment/emotion bearing words, and parts-of-speech information is most effective for gleaning emotions. The highest accuracy (82.35%) is achieved with a training data containing about 3700 tweets.

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.

Twitter Sentiment Analysis using Machine Learning and Knowledge-based Approach

International Journal of Computer Applications, 2014

Sentiment analysis is mainly concerned with identifying and classifying opinions or emotions that are expressed within a text. These days, sharing opinions and expressing emotions through social networking websites has become very common. Therefore, a large amount of data is generated each day, on which mining can be effectively performed to retrieve quality information. Sentiment analysis on such data can prove to be instrumental in generating an aggregated opinion on certain products. Twitter sentiment analysis often becomes a difficult task due to the presence of slangs and misspellings. Also, we constantly encounter new words, which makes it more difficult to analyze and compute the sentiment as compared to the usual sentiment analysis. Twitter restricts the length of a tweet to 140 characters. Thus, extracting valuable information from short texts is yet another challenge. Knowledge-based approach and

Affect in Tweets using Experts Model

ArXiv, 2018

Estimating the intensity of emotion has gained significance as modern textual inputs in potential applications like social media, e-retail markets, psychology, advertisements etc., carry a lot of emotions, feelings, expressions along with its meaning. However, the approaches of traditional sentiment analysis primarily focuses on classifying the sentiment in general (positive or negative) or at an aspect level(very positive, low negative, etc.) and cannot exploit the intensity information. Moreover, automatically identifying emotions like anger, fear, joy, sadness, disgust etc., from text introduces challenging scenarios where single tweet may contain multiple emotions with different intensities and some emotions may even co-occur in some of the tweets. In this paper, we propose an architecture, Experts Model, inspired from the standard Mixture of Experts (MoE) model. The key idea here is each expert learns different sets of features from the feature vector which helps in better emot...

Emotion Classification of Twitter Data Using an Approach Based on Ranking

Research in Computing Science

In this work, a model for textual emotion classification based on Ranking technique is presented. The Ranking technique uses the frequencies of words in order to assign a relevance for each in a tweets (Spanish) after calculating the total relevance of the tweet for each classes. The classes are associated to four emotions: happiness, sadness, anger and fear and the highest relevance indicates to which class the tweet belongs. The training and test corpora are created by manually selected key words as references for a crawling tool, both contain manually tagged tweets extracted from Twitter; the training corpus was validated by K-Fold Cross Validation having a 90% of acceptance. The results are compared with Naïve Bayes and Bigrams Probabilities models using precision, recall and F-measure.