Music sentiment and stock returns

This overview is based on the academic paper entitled “Music sentiment and stock returns” co-authored by Adrian Fernandez-Perez, Alexandre Garel and Ivan Indriawan, and is published in Economic Letters.

Investor sentiment can be explained as the attitude among investors about a specific market or asset, that future cash flows and investment risks are not only justified by the facts at hand but are also driven by emotion. The biggest issue in the research literature is finding a reliable measure that can capture investor sentiment. As a result, mood proxies have emerged as a viable alternative to survey- or market-variable-based indicators. Prior studies relied on events that were likely to affect the mood of individuals, like weather conditions, the outcome of major sporting events, or aviation disasters, to pick up these mood swings. In our paper, we propose an alternative way to capture the mood of individuals at any given point in time by looking at their music choices.

Psychology literature shows that music choices reveal the mood of listeners. Research in the field of musical psychology documents strong relationships between emotions and psychophysical elements. Also, research in personality and social psychology shows how individual differences in musical preferences are linked to personality traits, values, and the way we think.

While earlier research establishes a link between music choices and people’s emotions, a critical empirical challenge is to associate mood states more precisely to quantifiable song characteristics. In this respect, our paper uses the valence (attracting or repelling forces)of a song, which quantifies the musical positiveness it conveys. In our paper, we assess the mood of individuals in the United States based on the U.S. Top-200 songs played on Spotify over the 2017-2019 period.

Our research shows that music sentiment is consistent with mood swings of individuals, we see a strong positive association with U.S. holidays and weekends and a strong negative association with returning to work, winter seasons, and adverse weather conditions. Next, we looked at the relationship between music sentiment and stock market returns. Earlier research shows that when an investor attitude is highly positive, prices are temporarily high, but prices return to normal when attitudes stabilize, reflecting a pattern of mispricing correction. We find that music sentiment is linked with a substantial price reversal pattern and that this reversal is more robust for higher mood-influenced stocks, which is consistent with sentiment-induced mispricing.

The key takeaway of our study is that the music we listen to gives voice to emotions that cannot be expressed in words. These emotions reveal seasonal, and weather-induced mood swings and are associated with a systematic pattern of mispricing correction in stock returns.