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
Product Context Analysis with Twitter Data
Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
2016 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Context. For the product manager, the product context analysis, which aims to align their products to the market needs, is very important. By understanding the market needs, the product manager knows the product context information about the environment the products conceived and the business the products take place. The product context analysis using the product context information helps the product manager find the accurate position of his/her products and support the decision-making of the products. The product context information generally could be found in the user feedbacks. And the traditional techniques of acquiring the user feedbacks can be replaced by collecting the existed online user feedbacks with a cheaper cost. Therefore, researchers did studies on the online user feedbacks and the results showed those user feedbacks contain the product context information. Therefore, in this study, I tried to elicit the product context information from the user feedbacks posted on Twitter.

Objectives. Objectives of this study are 1. I investigated what kinds of Apps can be used to collect   more related Tweets, and 2. I investigated what kinds of product context information can be elicited from the collected Tweets.

Methods. To achieve the first objective, I designed unified criteria for selecting Apps and collecting App-related Tweets, and then conduct the statistical analysis to find out what is/are the factor(s) affect (s) the Tweets collection. To achieve the second objective, I conducted the directed content analysis on the collected Tweets with an indicator for identifying the product context information, and then make a descriptive statistical analysis of the elicited product context information.

Results. I found the top-ranked Apps or Apps in few themes like “Health and Fitness” and “Games” have more and fresher App-related Tweets. And from my collected Tweets, I can elicit at least 15 types of product context information, the types include “user experience”, “use case”, “partner”, “competitor”, “platforms” and so on.

Conclusions. This is an exploratory study of eliciting product context information from the Tweets. It presented the method of collecting the App-related Tweets and eliciting product context information from the collected Tweets. It showed what kinds of App are suitable to do so and what types of product context information can be elicited from the Tweets. This study let us be aware of that the Tweets can be used for the product context analysis, and let us know the appropriate condition to use the Tweets for the product context analysis.

Place, publisher, year, edition, pages
2016. , 51 p.
Keyword [en]
Twitter, product context information, content analysis
National Category
Software Engineering
Identifiers
URN: urn:nbn:se:bth-13526OAI: oai:DiVA.org:bth-13526DiVA: diva2:1051722
Subject / course
PA2534 Master's Thesis (120 credits) in Software Engineering
Educational program
PAAPX Master of Science Programme in Software Engineering
Presentation
2016-09-26, J1650, Valhallavägen 1, Karlskrona, 13:00 (English)
Supervisors
Examiners
Available from: 2016-12-05 Created: 2016-12-02 Last updated: 2016-12-05Bibliographically approved

Open Access in DiVA

fulltext(3450 kB)73 downloads
File information
File name FULLTEXT02.pdfFile size 3450 kBChecksum SHA-512
54cdbaa1cd24eb7bfa12413ad1ee694364dee7f0d60f3369e303552f15a73e4ea8cff88ed5abc857990c41eccaf1bffe8031a937f44b6469936f0b475111390c
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Sun, Tao
By organisation
Department of Software Engineering
Software Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 73 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

Total: 221 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