Text Mining Implementation of Text Mining to Know Someone's Social Pattern Based on Tweet on Twitter
Implementation of Text Mining to Know Someone's Social Pattern Based on Tweet on Twitter
AbstractTwitter social networks are information technologies that allow users to access the information they disseminate. Twitter activities in Indonesia use many of Twitter's features to present all forms of information that he wants to write. Verbal communication on Tweet may be one of those who identify social patterns. Currently, human social models are necessary for personal or group interests. Information about social models can also be used to make effective and efficient decisions without the help of a psychologist. Then it takes time and special knowledge to reveal a lot of tweets. To cope with this, a system will be created that can identify social models of a person based on tweet on Twitter. Tweet is acquired and processed using text mining. Then, in the classification process, the naive Bayes classifier method will be used. Text mining methods and the naive Bayes classifier method have been successfully applied in defining social patterns in the system. There are 4 tests, such as: K-fold Cross Validation testing, Blackbox Testing, Questionnaire, and Psychologist Validity. From these tests it can be concluded that the system has been tested for functionality, and obtained an accuracy of 96% from the K-fold Cross Validation and 90% from the validity of the psychologist. Keywords: Information Technology, Social Media, Twitter, Tweet, Text Mining, Naive Bayes Classifier
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.