Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Sentiment Analysis of Twitter Data Using Machine Learning and Deep Learning Methods
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Background: Twitter, Facebook, WordPress, etc. act as the major sources of information exchange in today's world. The tweets on Twitter are mainly based on the public opinion on a product, event or topic and thus contains large volumes of unprocessed data. Synthesis and Analysis of this data is very important and difficult due to the size of the dataset. Sentiment analysis is chosen as the apt method to analyse this data as this method does not go through all the tweets but rather relates to the sentiments of these tweets in terms of positive, negative and neutral opinions. Sentiment Analysis is normally performed in 3 ways namely Machine learning-based approach, Sentiment lexicon-based approach, and Hybrid approach. The Machine learning based approach uses machine learning algorithms and deep learning algorithms for analysing the data, whereas the sentiment lexicon-based approach uses lexicons in analysing the data and they contain vocabulary of positive and negative words. The Hybrid approach uses a combination of both Machine learning and sentiment lexicon approach for classification.

Objectives: The primary objectives of this research are: To identify the algorithms and metrics for evaluating the performance of Machine Learning Classifiers. To compare the metrics from the identified algorithms depending on the size of the dataset that affects the performance of the best-suited algorithm for sentiment analysis.

Method: The method chosen to address the research questions is Experiment. Through which the identified algorithms are evaluated with the selected metrics.

Results: The identified machine learning algorithms are Naïve Bayes, Random Forest, XGBoost and the deep learning algorithm is CNN-LSTM. The algorithms are evaluated with respect to the metrics namely precision, accuracy, F1 score, recall and compared. CNN-LSTM model is best suited for sentiment analysis on twitter data with respect to the selected size of the dataset.

Conclusion: Through the analysis of results, the aim of this research is achieved in identifying the best-suited algorithm for sentiment analysis on twitter data with respect to the selected dataset. CNN-LSTM model results in having the highest accuracy of 88% among the selected algorithms for the sentiment analysis of Twitter data with respect to the selected dataset.

Place, publisher, year, edition, pages
2019. , p. 46
Keywords [en]
Machine Learning, Sentiment Analysis, Twitter data, Deep Learning, Naïve Bayes, Twitter Sentiment Analysis
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:bth-18447OAI: oai:DiVA.org:bth-18447DiVA, id: diva2:1335995
Subject / course
DV2572 Master´s Thesis in Computer Science
Educational program
DVADA Master Qualification Plan in Computer Science
Supervisors
Examiners
Available from: 2019-07-11 Created: 2019-07-08 Last updated: 2019-07-11Bibliographically approved

Open Access in DiVA

BTH2019ReddyManda(1257 kB)84 downloads
File information
File name FULLTEXT02.pdfFile size 1257 kBChecksum SHA-512
002d38e1c928494e87473881562be14d24525f1916d9ee4abaa8821cc2687429425a59fb2949fff33e91337021b5bac4fea82671b3df74cf2e34ac7a2d43ba55
Type fulltextMimetype application/pdf

By organisation
Department of Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 84 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 250 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf