Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/70419
Title: A study on spread pattern of online social networks rumour
Authors: Yang, Chenyan
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2017
Abstract: This project studies the spread pattern of verified rumours on online social media networks. The project is scoped to the Twitter social media platform for the aim of characterizing and summarizing significant features of well spread rumours. There have been significant challenges throughout this project. The difficulty lies in the massive computational needs to perform retrieval and data processing of the large volume of tweets. Other challenges include but are not limited to the rarity of finding a meaningful, believable rumours which has impeded the analysis process of this project. The methodology for characterising spread patterns of rumours starts by mass data collection via Twitter API. This was done with a custom script and the source is included together with this report. The next stage of the process is to perform user analysis to find the correlation between user actions and the spread patterns. This is then followed by performing semantic analysis on tweet replies to find the general mood of the users. Finally, data aggregation is done to draw statistical meaning. It can be concluded from this project that there are indeed specific features that can be observed from the spread pattern of rumours.
URI: http://hdl.handle.net/10356/70419
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_SCE16-0461_YANG CHENYAN_U1422724G.pdf
  Restricted Access
2.63 MBAdobe PDFView/Open

Page view(s)

144
Updated on Jun 22, 2021

Download(s) 50

29
Updated on Jun 22, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.