Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Intelligent System for the Prediction of Emotions via Text Mining


Affiliations
1 Department of Computer Science and Engineering, K .C.G College of Technology, Chennai, India
2 Department of Computer Science and Engineering, K .C.G College of Technology, Chennai, India
     

   Subscribe/Renew Journal


The main stay of this project is to find the connections between emotions and affective terms by categorizing the web-content, based on the emotion present in it and also predicting the emotions from text automatically. Emotions can provide a new aspect for categorizing different documents, and therefore it will be useful for online users to select related documents based on their emotional preferences. In order to predict the emotion contained in a text, a joint emotion topic model by augmenting Latent Dirichlet Allocation (LDA) with an additional layer for emotion modeling is used. Using this, it first generates a set of latent topics from emotions, followed by generating emotional terms from each topic., which finally provides  a specific emotion for a particular content or text from a document-specific emotional distribution. The emotion-topic model utilizes the complementary advantages of both emotion-term model and emotion-topic model. Emotion-topic model allows associating the terms and emotions via topics which is more flexible and has better modeling potential. This model notably improves the performance of social emotion prediction.


Keywords

Affective Terms, Emotion Modelling, Emotion-Term Model, Latent Dirichlet Allocation (LDA).
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 235

PDF Views: 1




  • Intelligent System for the Prediction of Emotions via Text Mining

Abstract Views: 235  |  PDF Views: 1

Authors

Soumya Chandran
Department of Computer Science and Engineering, K .C.G College of Technology, Chennai, India
S. Bairavel
Department of Computer Science and Engineering, K .C.G College of Technology, Chennai, India

Abstract


The main stay of this project is to find the connections between emotions and affective terms by categorizing the web-content, based on the emotion present in it and also predicting the emotions from text automatically. Emotions can provide a new aspect for categorizing different documents, and therefore it will be useful for online users to select related documents based on their emotional preferences. In order to predict the emotion contained in a text, a joint emotion topic model by augmenting Latent Dirichlet Allocation (LDA) with an additional layer for emotion modeling is used. Using this, it first generates a set of latent topics from emotions, followed by generating emotional terms from each topic., which finally provides  a specific emotion for a particular content or text from a document-specific emotional distribution. The emotion-topic model utilizes the complementary advantages of both emotion-term model and emotion-topic model. Emotion-topic model allows associating the terms and emotions via topics which is more flexible and has better modeling potential. This model notably improves the performance of social emotion prediction.


Keywords


Affective Terms, Emotion Modelling, Emotion-Term Model, Latent Dirichlet Allocation (LDA).



DOI: https://doi.org/10.36039/ciitaas%2F6%2F3%2F2014%2F106779.85-90