Date of Award
Master of Science (MS)
Social media are shaping users' attitudes and behaviors through spreading information anytime and anywhere. Monitoring user opinions on social media is an effective solution to measure users' preferences towards brands or events. Currently, supervised machine learning-based methods dominate this area. However, as far as we know, there is no comprehensive comparison of performances of different models to figure out which model will be better for individual datasets. The focus of this thesis is to compare the performance of different supervised machine learning models. In detail, we built six classifiers, including support vector machine, random forest, neural network, Adaboost, decision tree, and Naive Bayes on two datasets and compare their performance. Furthermore, we introduced feature selection to remove unrelated attributes to preprocess the data and compare performance by building classifiers on the preprocessed data. Experimental results show that without feature selection, there is no significant difference in the performance. After feature selection, random forest outperformed other classifiers.
Prairie View A&M University
Rights© 2021 Prairie View A & M University
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Date of Digitization
John B Coleman Library
City of Publication
Hastings, C. (2020). Sentiment Analysis on Social Media Via Machine Learning. Retrieved from https://digitalcommons.pvamu.edu/pvamu-theses/3