Classifying Emotion in News Sentences: When Machine Classification Meets Human Classification
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 1
Abstract
Multiple emotions are often evoked in readers in response to text stimuli like news article. In this paper, we present a method for classifying news sentences into multiple emotion categories. The corpus consists of 1000 news sentences and the emotion tag considered was anger, disgust, fear, happiness, sadness and surprise. We performed different experiments to compare the machine classification with human classification of emotion. In both the cases, it has been observed that combining anger and disgust class results in better classification and removing surprise, which is a highly ambiguous class in human classification, improves the performance. Words present in the sentences and the polarity of the subject, object and verb were used as features. The classifier performs better with the word and polarity feature combination compared to feature set consisting only of words. The best performance has been achieved with the corpus where anger and disgust classes are combined and surprise class is removed. In this experiment, the average precision was computed to be 79.5% and the average class wise micro F1 is found to be 59.52%.
Authors and Affiliations
Plaban Kumar Bhowmick , Anupam Basu , Pabitra Mitra
Keywords
Related Articles
- EP ID EP123941
- DOI -
- Views 108
- Downloads 0
Technical challenges and Constraints for Spectrum Planning in GSM networks
GSM is the most widespread, most commonly deployed and fastest growing system standard for mobile telephony in the world. Even though UMTS, the third generation mobile system has entered the market. Network quality of se...
An Efficient Data Link Protocol for Integrated Wireless Networks: Next Generation Networks (NGN)
The seamless integrated communication has a vital role in pervasive communication. It has implemented on next generation networking. There is various integration issues: coupling, decoupling, mobility, IP etc. In this pa...
Optimal Solution Strategy for Games
In order to optimize a game, different techniques of optimization are available. Considering the far wide application of game theory it becomes essential to establish the most effective method of optimization of games. I...
Interaction between Software Engineering and Artificial Intelligence- A Review
Software engineering and artificial intelligence is the two field of the computer science. During the last decades, the disciplines of Artificial Intelligence and Software Engineering have developed separately without th...
Upgraded Selection Sort
Sorting is a technique which is frequently used in our day to day life. It has a direct implication on searching. If the data is sorted on any key attribute, finding data based on that key attribute becomes very fast. Th...