Is Bigger Always Better? Potential Biases of Big Data Derived from Social Network Sites

Abstract

This article discusses methodological challenges of using big data that rely on specific sites and services as their sampling frames, focusing on social network sites in particular. It draws on survey data to show that people do not select into the use of such sites randomly. Instead, use is biased in certain ways yielding samples that limit the generalizability of findings. Results show that age, gender, race/ethnicity, socioeconomic status, online experiences, and Internet skills all influence the social network sites people use and thus where traces of their behavior show up. This has implications for the types of conclusions one can draw from data derived from users of specific sites. The article ends by noting how big data studies can address the shortcomings that result from biased sampling frames.

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 — 267 citations exist upstream.

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