NORMA eResearch @NCI Library

Sentimental Analysis on the pharmaceutical drug reviews with Deep Learning and comparative study with ML algorithms

Shaik, Mobeen (2021) Sentimental Analysis on the pharmaceutical drug reviews with Deep Learning and comparative study with ML algorithms. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (714kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (964kB) | Preview


For any health issues, we usually have more than one proven system for treating the illness. This applies to the drugs that could be used for treatment. It's very obvious that we need to have a comparison mechanism to evaluate which drugs are the best from what is available in the market for usage. Sentiment analysis is one of the widely used techniques for collecting opinions from a large group of people using social media, blogs and different other sources as well. The traditional approach is using machine learning techniques to process the data and create a model that performs the sentiment classification. This research presents a comparative study of the traditional ML approach with the deep learning techniques in which we going to apply the concept of sentiment analysis for understanding the opinion in the medical drugs. In the research, we have compared the algorithms in the traditional machine learning techniques like Naive Bayes, generalized linear model (GLM), Logistic Regression (LR), Fast Large Margin with the deep learning approaches like Artificial Neural Network(ANN) and Recurrent Neural Network(RNN) algorithms. We have materialized the code for the RNN algorithm which is Long short-term memory(LSTM) and the rest of the models are compared based on the results generated from the RapidMiner tool. For the vectorization, we have applied the concept of term frequency-inverse document frequency (TF-IDF). Finally, a system was built to classify the sentiment using the Flask Python framework.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > RS Pharmacy and materia medica
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 10 Mar 2023 17:51
Last Modified: 10 Mar 2023 17:51

Actions (login required)

View Item View Item