PN 2021-04
The National Government's Role in Local Water Supply Delivery in the Philippines
Economic Triple Shock: Assessment and Remedial Measures
Policy Imperatives Moving Forward from the COVID-19 Crisis
A Results-Based Assessment of the Bayanihan to Heal as One Act
Publication Detail
JA 2018 8: Using Latent Dirichlet Allocation for Topic Modeling and Document Clustering of Dumaguete City Twitter Dataset

Online communication channel, such as social media is predominantly becoming common nowadays as it allows people to fearlessly and instantly share opinions and exchange information at one's convenience. One popular social media site and microblogging service, Twitter, has made it easy for people to express or share their experiences, adventures, and opinions on places they visited. These short messages, called tweets contain useful information that can be analyzed to generate topics of what people are talking about and their sentiments on that particular topic. To process these huge amounts of Twitter dataset requires substantial effort of information filtering just to successfully drill down relevant topics and determine sentiments of those topic clusters. This paper discusses the process and the methods of generating topics and topic clusters on Twitter dataset about Dumaguete City and generates a probable sentiment analysis of each topic clusters. Latent Dirichlet Allocation (LDA) model was used to generate topics out of 99,942 tweets and clusters the tweets by calculating the probability on which topic cluster the tweet belongs. A supervised machine learning algorithm, Support Vector Machine (SVM) was used to generalize the sentiment of each cluster into positive, negative, or neutral.

Silliman University
Authors Keywords
Montenegro, Chuchi; Cerino, Ligutom; Orio, Jay VIncent; Ramacho, Dyannah Alexa Marie; social media; Latent Dirichlet Allocation; sentiment analysis ;
Download PDF Number of Downloads
Published in 2018 and available for Downloaded 0 times since March 05, 2021
Please let us know your reason for downloading this publication. May we also ask you to provide additional information that will help us serve you better? Rest assured that your answers will not be shared with any outside parties. It will take you only two minutes to complete the survey. Thank you.

To use as reference:
If others, (Please specify):
Name: (optional)
Email: (required, but will not display)
If Prefer to self-describe, please specify:
Level of Education:
If employed either part-time or full-time, name of office:
If others, (Please specify):
Would you like to receive the SERP-P UPDATES e-newsletter? Yes No
Use the space below if you have any comment about this publication or SERP-P knowledge resources in general.