Rule-based agent for social media sentiment detection

Current technology use the beneficial from social media as their vehicle to do multiple processes that incorporate social media participation in its many forms. Social media is a great “hub” to get closer with the citizens. Sentiment analysis is the area that able to monitor the social media activities from such processes and functions acquired especially on the posting and comments publicly send. In this paper, the rule-based method is proposed that been derived from an agent to help social media communication platform such as Facebook and Twitter to do various sentiment detection. By formulating of rule-based method is to ensure that only suitable and optimized rules will be chosen for the implementation of the sentiment detection. The newly formulated rule-based method enable agent to generate few task using Semantic Role Labeling technique especially on text processing to filter and classify the content data set, advancing the state of the art in sentiment detection approaches. In particular, this work is novel in its proposed new rule-based techniques to manipulate the sentiment detection in social media and also for improving the quality of sentiment analysis.