Classification of Emotion and Polarity from Twitter Data

Hamad, Rebeen Ali (2016) Classification of Emotion and Polarity from Twitter Data. [Dissertation (University of Nottingham only)]

[img] PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (4MB)

Abstract

Classification of public information from microblogging and social networking services could yield interesting outcomes and insights into the social public opinions towards different services and products. Microblogging and social networking data is one of the most helpful and proper indicators of public opinion. Hence, in this research real time Twitter microblogging data towards iPad and iPhone have been collected in different locations in order to analyse and classify data in terms of polarity: positive or negative, and emotion: anger, joy, sadness, disgust, fear, and surprise. After that the collected tweets have been pre-processed to generate document level ground truth. Supervised machine learning algorithms have been used to classify tweets to their classes using cross validation and partitioning the data across cities. The performance measures of the classifiers have been considered to identify suitable algorithm for the data sets. It was found that the K-NN, Naïve Bayes, and SVM have a reasonable accuracy rates, however, the K-NN has outperformed the Naïve Bayes, SVM, and ZeroR based on the achieved accuracy rates and trained model time. The K-NN has achieved the highest accuracy rates 96.58 % and 99.94 % for the iPad and iPhone emotion data sets using cross validation technique respectively. Regarding partitioning the data per city, the K-NN has achieved the highest accuracy rates 98.8% and 99.95% for the iPad and iPhone emotion data sets respectively. Regarding the polarity data sets using both cross validation and partitioning data per city the K-NN achieved 100% for the all polarity data sets.

Item Type: Dissertation (University of Nottingham only)
Depositing User: Gonzalez-Orbegoso, Mrs Carolina
Date Deposited: 18 Jan 2017 12:19
Last Modified: 19 Jan 2017 18:06
URI: http://eprints.nottingham.ac.uk/id/eprint/39176

Actions (Archive Staff Only)

Edit View Edit View