Searching and Clustering Methodologies

Abstract

People create, consume, and share content online in increasingly complex ways, often including multiple news, entertainment, and social media platforms. This article explores methods for tracing political media content across overlapping communication infrastructures. Using the 2011 Occupy Movement protests and 2013 consumer boycotts as cases, we illustrate methods for creating integrated datasets of political event-related social media content by (1) using fixed URLs to link posts across platforms ( URL-based integration) and (2) using semiautomated text clustering to identify similar posts across social networking services ( thematic integration). These approaches help to reveal biases in the way that we characterize political communication practices that may occur when we focus on a single platform in isolation.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 16 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.