Twitter Analytics of the K-12 Education Program of the Philippines Using Aylien in Rapidminer

AUTHOR/S: Novie Joy C. Pelobello, Raul Vincent W. Lumapas, Adrian D. Ablazo

DATE COMPLETED: August 1, 2016

KEYWORDS: Philippine K-12 Education Program, Educational Data Mining, Sentiment Analysis, RapidMiner Aylien, Twitter Analytics


            This research performed twitter mining to obtain information about the opinion of the people towards the new K-12 education program of the Philippines as the discussed topic. It acquires opinion poll from Twitter microblogs to obtain the general sentiment of the K-12 education system. Specifically, it generates a three-way sentiment polarity in terms of positive, negative and neutral sentiments.

            It also explores the use of RapidMiner as a platform to perform analytics on Twitter data. Researchers used various RapidMiner operators to process the Twitter microblogs and generate sentiment analysis. Specifically, it utilized AYLIEN as an extension module of RapidMiner for text analysis and extract insights from these tweets. 

            This paper shows that most of the sentiments about the K-12 education system on Twitter are neutral sentiments. Most of the tweets simply convey information about the K-12 program and do not show a positive or negative opinion. The experiment also reveals in word cluster analysis that users who expressed sentiments about K-12 used similar words on the messages they posted. Overall, the results suggest that tweet data have a quite peculiar nature. Words used in discussed topic create a sort of Twitter culture. This study also runs a predictive model using a simple decision tree. It appears in the decision tree generated that only favorites variable or the number of likes on a K-12 tweet provides a strong indication of classifying a K-12 tweet as subjective or objective. 

Request for Full Article (Please fill in the needed details. We will promptly respond to your request thru your e-mail.)

[contact-form-7 404 "Not Found"]