Classification of Comments Regarding the Politeknik Caltex Riau Using the Naive Bayes Algorithm from Instagram Social Media
AbstractInstagram Politeknik Caltex Riau is one of the social media used by the Riau Caltex Polytechnic for media promotion of various activities, achievements and other matters related to the Caltex Riau Polytechnic. Instagram Politeknik Caltex Riau was created in 2015. Of the various posts on the @politeknikcaltexriau account, there are many comments that are critical, input, and questions. So that these comments can be used by the Riau Caltex Polytechnic by classifying comments based on the categories needed by the Caltex Riau Polytechnic. Therefore, we need a system that can perform the comment classification process using text mining that utilizes the Naive Bayes algorithm. With this system, it is expected to know the percentage and pattern of public comments on the @politeknikcaltexriau account per category and the trend of comments in certain months. Based on the results of tests carried out on the classification system that was built, using blackbox testing, it was found that 100% of the system's functionality was running well. Furthermore, text mining techniques and the Naive Bayes algorithm have been successfully adapted to this system in categorizing Instagram comments on the @politeknikcaltexriau account. The system has been tested for functionality and has an average accuracy of 72.911%. Keywords: comment classification, text mining and naÃ¯ve bayes
Copyright info for authors
1. Authors hold the copyright in any process, procedure, or article described in the work and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors retain publishing rights to re-use all or portion of the work in different work but can not granting third-party requests for reprinting and republishing the work.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.