Personalized Ontology Based on Consumer Emotion and Behavior Analysis

This paper will document the relationship between the consumer and their behaviors. Using this technique the consumers can use the web to find the information about the product and services. Ontologism can be constructed manually using ontology but the process can be tedious. The integration of knowledge acquisition with machine learning facilitates research toward automating the ontology generation process. Many approaches have been investigated for generating ontology. These include Natural Language Processing (NLP) techniques association rule mining hierarchical clustering translation from relational databases and Formal Concept Analysis. However these techniques focus mainly on constructing concept hierarchies from text documents or relational databases. They can also be used to find groups of people with similar interests. A major problem of traditional association rule mining techniques is that each item in a transaction is considered only to either exist or not. Thus, the user's preference and interest in each transaction item cannot be precisely represented. Since the concepts of preference and interest are fuzzy data fuzzy logic can be applied. For example combine fuzzy association rule mining and case-based reasoning (CBR) to improve the quality of web access pattern prediction. The fuzzy rule set was found to perform better in prediction accuracy and rule coverage than traditional rule set.