Systematically Monitoring Social Media: The Case of the German Federal Election 2017

Abstract

It is a considerable task to collect digital trace data at a large scale and at the same time adhere to established academic standards. In the context of political communication, important challenges are (1) defining the social media accounts and posts relevant to the campaign (content validity), (2) operationalizing the venues where relevant social media activity takes place (construct validity), (3) capturing all of the relevant social media activity (reliability), and (4) sharing as much data as possible for reuse and replication (objectivity). This project by GESIS – Leibniz Institute for the Social Sciences and the E-Democracy Program of the University of Koblenz-Landau conducted such an effort. We concentrated on the two social media networks of most political relevance, Facebook and Twitter.

An Evaluation of Retrospective Facebook Content Collection

“…Another possibility would be a coordinated data collection effort-if the scope of public data access remains sufficient for such an endeavor. The "Social Media Monitoring" initiative by GESIS (Kaczmirek et al, 2014;Stier et al, 2018) is an interesting step in this direction. Yet the project is also confronted with many legal and ethical challenges beyond the technical implementation, ranging from data and privacy protection to copyright and the platforms' terms and conditions.…”

“…A comparison of both data sets revealed that the retrospectively collected data set missed a non-negligible amount of content compared to the rolling collection. The authors consequently decided to publish the latter data set (Stier et al, 2018).…”

“…Facebook is the online social network site with the greatest reach in most countries and it is considered an important platform for political communication. Scholars investigated, for example, how political parties communicate on Facebook (Arzheimer, 2015;Magin, Podschuweit, Haßler, & Russmann, 2016;Stier et al, 2018;Stier, Posch, Bleier, & Strohmaier, 2017), how users interact with posts from media organizations' pages (Schmidt et al, 2017), or which (media) sources were referred to by parties and their followers on political pages (Bachl, 2018).…”

Measuring Proximity Between Newspapers and Political Parties: The Sentiment Political Compass

“…A rich corpus of work on prediction and analysis focuses on specific events with a large political scope. Since our work examines the political landscape in Germany, we particularly highlight a few papers concerned with the German Federal Elections in 2009 (Jungherr, Jürgens, & Schön, ; Tumasjan, Sprenger, Sandner, & Welpe, ), in 2013 (Jungherr, Schön, & Jürgens, ; Kaczmirek et al, ) and in 2017 (Stier et al, ). The working paper by Stier et al () like the present study, analyzes the German Federal Elections of 2017.…”

Redundancy Reduction in Twitter Event Streams

“…• Analysis of the political representativeness of Twitter users [3] • Real-time Twitter analysis [4][5][6] • Democratic elections [7][8][9][10][11][12][13] • The uses of Twitter by populists [14] • Misinformation dissemination and event detection in social networks [15][16][17] • Online public shaming [18] • and many more Furthermore, there exist plenty of public available datasets. E.g., a curated collection [19] is hosted on Zenodo [20] and covers several datasets of political campaigns [8,9], online misinformation networks [21], event detection in temporal networks [22], public shaming [23], Twitter-related word vectors [24], retweeting timeseries [25], and even continuously updated samples of a nations-wide Twitter usage [26].…”