Return to search

Multimodal Data Fusion As a Predictior of Missing Information in Social Networks

abstract: Over 2 billion people are using online social network services, such as Facebook, Twitter, Google+, LinkedIn, and Pinterest. Users update their status, post their photos, share their information, and chat with others in these social network sites every day; however, not everyone shares the same amount of information. This thesis explores methods of linking publicly available data sources as a means of extrapolating missing information of Facebook. An application named "Visual Friends Income Map" has been created on Facebook to collect social network data and explore geodemographic properties to link publicly available data, such as the US census data. Multiple predictors are implemented to link data sets and extrapolate missing information from Facebook with accurate predictions. The location based predictor matches Facebook users' locations with census data at the city level for income and demographic predictions. Age and relationship based predictors are created to improve the accuracy of the proposed location based predictor utilizing social network link information. In the case where a user does not share any location information on their Facebook profile, a kernel density estimation location predictor is created. This predictor utilizes publicly available telephone record information of all people with the same surname of this user in the US to create a likelihood distribution of the user's location. This is combined with the user's IP level information in order to narrow the probability estimation down to a local regional constraint. / Dissertation/Thesis / M.S. Computer Science 2012

Identiferoai:union.ndltd.org:asu.edu/item:15902
Date January 2012
ContributorsMao, Jingxian (Author), Maciejewski, Ross (Advisor), Farin, Gerald (Committee member), Wang, Yalin (Committee member), Arizona State University (Publisher)
Source SetsArizona State University
LanguageEnglish
Detected LanguageEnglish
TypeMasters Thesis
Format72 pages
Rightshttp://rightsstatements.org/vocab/InC/1.0/, All Rights Reserved

Page generated in 0.0017 seconds