When it comes to predicting market behaviour, social media is more than just noise. After analyzing millions of investor posts, Assistant Professor Runjing Lu of the Department of Economics and her co-authors have shown that social media can yield valuable signals for understanding financial markets. The key to unlocking these signals means distinguishing between how investors feel, or their sentiment, and what investors choose to focus on, or their attention.

The study, Market Signals from Social Media, examined millions of daily posts made on three different social media platforms between 2013 and 2021.

“We constructed indexes using data from StockTwits, Twitter, and Seeking Alpha, platforms where investors actively post,” Professor Lu explained. “What’s unique is that we separate sentiment from attention. On these platforms, users express both their opinions about how bearish or bullish they are about a stock, which gives us sentiment, and their focus of discussion, the stocks they talk about, which gives us attention. We then aggregated these signals across firms and platforms to create separate daily indexes for sentiment and attention that reflect overall market mood and focus.” [Read more…]