Classification of Emotion and Polarity from Twitter Data
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 p...
| Main Author: | |
|---|---|
| Format: | Dissertation (University of Nottingham only) |
| Language: | English |
| Published: |
2016
|
| Online Access: | https://eprints.nottingham.ac.uk/39176/ |
| _version_ | 1848795780772528128 |
|---|---|
| author | Hamad, Rebeen Ali |
| author_facet | Hamad, Rebeen Ali |
| author_sort | Hamad, Rebeen Ali |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-14T19:37:32Z |
| format | Dissertation (University of Nottingham only) |
| id | nottingham-39176 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T19:37:32Z |
| publishDate | 2016 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-391762017-10-19T17:38:27Z https://eprints.nottingham.ac.uk/39176/ Classification of Emotion and Polarity from Twitter Data Hamad, Rebeen Ali 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. 2016-12-14 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/39176/1/Rebeen%20Ali%20Hamad.pdf Hamad, Rebeen Ali (2016) Classification of Emotion and Polarity from Twitter Data. [Dissertation (University of Nottingham only)] |
| spellingShingle | Hamad, Rebeen Ali Classification of Emotion and Polarity from Twitter Data |
| title | Classification of Emotion and Polarity from Twitter Data |
| title_full | Classification of Emotion and Polarity from Twitter Data |
| title_fullStr | Classification of Emotion and Polarity from Twitter Data |
| title_full_unstemmed | Classification of Emotion and Polarity from Twitter Data |
| title_short | Classification of Emotion and Polarity from Twitter Data |
| title_sort | classification of emotion and polarity from twitter data |
| url | https://eprints.nottingham.ac.uk/39176/ |