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 93
- Downloads 0
AN INTELLIGENT APPROACH OF WEB DATA MINING
With an explosive growth of the World Wide Web, websites are playing an important role in providing an information and knowledge to the end users. Web usage patterns are an important aspect to discover hidden and meaning...
M-Band Graphic Equalizer
This paper deals with the concept of filter banks. Filter banks are a group of band-pass filters connected in parallel. Each parallel connection forms a channel for different frequency-bands present in the input signal....
A Novel Pair of Replacement Algorithms for L1 and L2 Cache for FFT
Processors speed is much faster than memory; to bridge this gap cache memory is used. This paper proposes a preeminent pair of replacement algorithms for Level 1 cache (L1) and Level 2 cache (L2) respectively for the Fas...
SOFTWARE ARCHITECTURE RECOVERY WITH ERROR TOLERANCE AND PENALTY COST IN GRAPH MINING
In the vast literature Software architecture has been recovered through graphs During Software Architecture recovery generally matching will takes place between Source graph and Query graph. Graph matching is one of the...
Centrality measures with a new index called E-User (Effective User) Index for determiningthe most effective user in Twitter Online Social Network
In this study, we considered the issue of determination of the most effective user in the twitter online social network. We worked on asocial network graph which have relationships (edges) between users who posteda tweet...