Twitter Data Warehouse and Business Intelligence Using Dimensional Model and Data Mining

Sentiment analysis is used to analyze data in text format such as tweets from Twitter social media users. Twitter is one of the most popular social media with more than half a billion users and can generate large volumes of data. It is difficult to operate large-scale data, so the data warehouse can...

Full description

Saved in:

Bibliographic Details
Published in:	2022 IEEE International Conference of Computer Science and Information Technology (ICOSNIKOM) pp. 1 - 6
Main Authors:	Togatorop, Parmonangan R., Sitorus, Dody, Purba, Yohana, Tarigan, Andika M. F.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 19-10-2022
Subjects:	Analytical models Blogs COVID-19 Data warehouses dimensional model lexicon based Sentiment analysis social media Social networking (online) Warehousing
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Sentiment analysis is used to analyze data in text format such as tweets from Twitter social media users. Twitter is one of the most popular social media with more than half a billion users and can generate large volumes of data. It is difficult to operate large-scale data, so the data warehouse can be used as a data storage area that allows the operation of large-scale data. The final step of data warehousing is the application of business intelligence. This research uses dimensional model approach to build data warehouse from Twitter and uses lexicon-based approach to analyze public opinion of Twitter users toward covid-19 vaccine in Indonesia. The results show that the creation of a data warehouse and sentiment analysis have been successfully carried out based on the evaluation of the data warehouse and sentiment analysis. The evaluation carried out on the data warehouse is to examine the components of the dimensional model based on indicators and dimensional modeling rules by Kimball. While the evaluation carried out on sentiment analysis is the confusion matrix with the result of the accuracy of sentiment analysis is 74%.
DOI:	10.1109/ICOSNIKOM56551.2022.10034904