Prasisto, Davega Putra and Purnama, James and Eng, Kho I (2019) Development of Sentiment Analysis of Instagram Comments for Social Media Influencer Online Marketplace. Bachelor thesis, Swiss German University.

Preview	Text Devaga Prasisto 11402011 TOC.pdf Download (1MB) | Preview
	Text Devaga Prasisto 11402011 1.pdf Restricted to Registered users only Download (777kB)
	Text Devaga Prasisto 11402011 2.pdf Restricted to Registered users only Download (338kB)
	Text Devaga Prasisto 11402011 3.pdf Restricted to Registered users only Download (1MB)
	Text Devaga Prasisto 11402011 4.pdf Restricted to Registered users only Download (312kB)
	Text Devaga Prasisto 11402011 5.pdf Restricted to Registered users only Download (624kB)
	Text Devaga Prasisto 11402011 6.pdf Restricted to Registered users only Download (1MB)
Preview	Text Devaga Prasisto 11402011 Ref.pdf Download (716kB) | Preview

Abstract

Influencers is increasingly being utilized in word of mouth social media marketing and various online platforms has appeared that serves as a marketplace that connect clients with influencers and offering various services, including assessing the general perception of the marketing campaign. Such assessment is made by analyzing the comments affiliated with the social media posts by influencers of the marketing campaign, which could be difficult to perform manually due to the potentially large amount of comments. As such, this research proposes the development of a lexiconbased sentiment analysis system for social media influencer online marketplace. The sentiment analysis system would be able to differentiate Instagram comments that are irrelevant to the Instagram post and would be able to classify the sentiment polarity. The sentiment analysis system is developed based on waterfall software development life cycle model and subjectivity measurement is adopted as an approach to measure its performance as indicated by four different metrics: Accuracy, Precision, Recall, and F1-measure. The result show that the proposed sentiment analysis system could reliably classify Instagram comments that is relevant to its affiliated Instagram post and express positive sentiment, but improvements need to be made on the classification on other categories.

Item Type:	Thesis (Bachelor)
Uncontrolled Keywords:	Sentiment Analysis ; Influencer ; Waterfall Methodology ; SentiStrength ; Lexicon-based Approach
Subjects:	H Social Sciences > HM Sociology > HM742 Online social networks T Technology > T Technology (General) > T58.5 Information technology
Divisions:	Faculty of Engineering and Information Technology > Department of Information Technology
Depositing User:	Adityatama Ratangga
Date Deposited:	19 May 2020 13:51
Last Modified:	19 May 2020 13:51
URI:	http://repository.sgu.ac.id/id/eprint/616

Actions (login required)

View Item