Google search trends and stock markets: Sentiment, attention or uncertainty?
利用弹性网络回归从77个国际股票市场中筛选投资者相关搜索词，构建中性且通用的谷歌搜索趋势指数，发现其反映不确定性叙事，并与市场不确定性指标高度相关，能有效预测股票收益和波动。
Keyword based measures purporting to reflect investor sentiment attention or uncertainty have been increasingly used to model stock market behaviour. We investigate and shed light on the narrative reflected by Google search trends (GST) by constructing a neutral and general stock market-related GST index. To do so e apply elastic net regression to select investor relevant search terms using a sample of 77 international stock markets. The index peaks around significant events that impacted global financial markets moves closely with established measures of market uncertainty and is predominantly correlated with uncertainty measures in differences implying that GST reflect an uncertainty narrative. Returns and volatility for developed emerging and frontier markets widely reflect changing Google search volumes and relationships conform to a prior expectations associated with uncertainty. Our index performs well relative to existing keyword-based uncertainty measures in its ability to approximate and predict systematic stock market drivers and factor dispersion underlying return volatility both in-sample and out-of-sample. Our study contributes to the understanding of the information reflected by GST their relationship with stock markets and points towards generalisability thus facilitating the development of further applications using search and return data.