Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/50138

Sampling Social Media: Supporting Information Retrieval from Microblog Data Resellers with Text, Network, and Spatial Analysis

File Size Format  
paper0251.pdf 367.22 kB Adobe PDF View/Open

Item Summary

Title:Sampling Social Media: Supporting Information Retrieval from Microblog Data Resellers with Text, Network, and Spatial Analysis
Authors:Buntain, Cody
McGrath, Erin
Behlendorf, Brandon
Keywords:Network Analysis of Digital and Social Media
computationally assisted data collection, data collection, elections, africa, information retrieval, sampling, social media, twitter
Date Issued:03 Jan 2018
Abstract:This paper presents a computationally assisted method for scaling researcher expertise to large, online social media datasets in which access is constrained and costly. Developed collaboratively between social and computer science researchers, this method is designed to be flexible, scalable, cost-effective, and to reduce bias in data collection. Online response to six case studies covering elections and election-related violence in Sub-Saharan African countries are explored using Twitter, a popular online microblogging platform. Results show: 1) automated query expansion can mitigate researcher bias, 2) machine learning models combining textual, social, temporal, and geographic features in social media data perform well in filtering data unrelated to the target event, and 3) these results are achievable while minimizing fee-based queries by bootstrapping with readily-available Twitter samples.
Pages/Duration:10 pages
URI/DOI:http://hdl.handle.net/10125/50138
ISBN:978-0-9981331-1-9
DOI:10.24251/HICSS.2018.251
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
Appears in Collections: Network Analysis of Digital and Social Media


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons