Mining Social Media: Finding Stories in Internet Data

Turning Social Media Into a Research Beat

Social platforms are often described as firehoses of content, but for reporters and researchers they can also be something else: a vast, messy, revealing archive. Mining Social Media is Lam Thuy Vo’s practical guide to working with that archive. Vo, a senior reporter at BuzzFeed News whose beat sits at the intersection of technology, society, and social media data, lays out an approach to finding stories in internet data without losing sight of the people behind the posts.

From Raw Posts to Reported Stories

The book treats social media as a source that requires method. Instead of treating viral moments as isolated curiosities, it shows how to frame questions, gather relevant material, and interpret what the data can and cannot say. That means moving between quantitative and qualitative research: counting and mapping patterns on one hand, reading context and meaning on the other.

What the Book Explores

• Internet research foundations: how to define a research question and think critically about platform data.
• Data mining concepts: collecting and organizing social media information for analysis.
• Social media as evidence: understanding the limits, biases, and ethical dimensions of online material.
• Story discovery: turning patterns, anomalies, and conversations into reportable narratives.
• Mixed methods: combining quantitative and qualitative approaches to build a fuller picture.

Who This Book Is For

Journalists, journalism students, researchers in media and social science, and anyone who needs to investigate social media data with care will find a grounded starting point here. The material is especially relevant for readers who want to understand how internet data can support accountability reporting and public-interest storytelling.

Why the Subject Matters

As social platforms shape public conversation, the ability to examine them responsibly becomes a core research skill. Vo’s experience covering misinformation, online hatred, and platform accountability gives the book a practical, newsroom-tested perspective. It is less about quick tricks and more about building a reliable process for asking better questions of internet data.

About the Author

Lam Thuy Vo is a senior reporter at BuzzFeed News. She has previously reported for The Wall Street Journal, Al Jazeera America, and NPR’s Planet Money, and has taught newsroom training programs and courses at the Craig Newmark CUNY Graduate School of Journalism. Her work focuses on technology, society, and the stories hidden in social media data.