Opinions mining of Twitter events using spatial-temporal features
By: Mudasir Mohd.
Contributor(s): Hashmy, Rana.
Publisher: New Delhi STM Journals 2018Edition: Vol 5 (2), May- Aug.Description: 36-44p.Subject(s): Computer EngineeringOnline resources: Click Here In: Journal of artificial intelligence research and advances (JoAIRA)Summary: Micro-blogs are a powerful tool to express an opinion. Twitter is one of the fastest growing micro-blog and has more than 900 million users. Twitter is a rich source of opinion as users share their daily experience of life and respond to specific events using tweets on twitter. In this paper, an automatic opinion classifier capable of automatically classify tweets into different opinion expressed by them is developed. Also manually annotated corpus for opining mining to be used by supervised learning algorithms is designed. Opinion classifier uses semantic, lexical, domain dependent and context features for classification. Results obtained confirm competitive performance and robustness of the system. Classifier accuracy is more than 75%, which is higher than the baseline accuracy.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2021-2021436 |
Micro-blogs are a powerful tool to express an opinion. Twitter is one of the fastest growing micro-blog and has more than 900 million users. Twitter is a rich source of opinion as users share their daily experience of life and respond to specific events using tweets on twitter. In this paper, an automatic opinion classifier capable of automatically classify tweets into different opinion expressed by them is developed. Also manually annotated corpus for opining mining to be used by supervised learning algorithms is designed. Opinion classifier uses semantic, lexical, domain dependent and context features for classification. Results obtained confirm competitive performance and robustness of the system. Classifier accuracy is more than 75%, which is higher than the baseline accuracy.
There are no comments for this item.