Evidence-based investing research
Value Investing Strategy (Strategy Overview)
Allocations for November 2026 (Final)
Cash TLT LQD SPY
Momentum Investing Strategy (Strategy Overview)
Allocations for November 2026 (Final)
1st ETF 2nd ETF 3rd ETF

Sentiment from Google Insights and Return Continuation

Steve LeCompte | | Posted in: Momentum Investing, Sentiment Indicators

Guide Market Indicators Sentiment

Key Insight

High Google search interest amplifies 4-week momentum continuation in S&P 500 stocks, with search-augmented winners continuing to advance and low-interest losers extending declines (214 stocks; 2004–2009; weekly returns).

Does investor interest in stocks as measured by Google Insights for Search predict which stocks will exhibit return continuation? In his June 2010 paper entitled “The Demand for Information”, Gordon Sims examines the effects of investor attention to stocks as defined by relative search frequency from Google Insights for Search (Stock Information Demand) to short-term stock momentum. The past return interval for momentum measurement is four weeks, augmented by a one-week delay in portfolio formation to avoid short-term reversal. Search term construction for Stock Information Demand focuses on intent to buy or sell a stock by appending “stock” or “quote” to a company’s name or ticker symbol. Using weekly returns for July 2003 through December 2009 for those S&P 500 stocks (as of July 31, 2003) with sufficient weekly Stock Information Demand data over the period 2004-2009 (214 stocks), he finds that:

  • Over the entire sample of stocks, there is no reliable continuation of past four-week return (plus skip-week), with or without consideration of Stock Information Demand.
  • However, there are potential indications for sample subsets:
    • Stocks with high Stock Information Demand that have increased in price over the last four weeks tend to continue advancing for the next four weeks, with no subsequent reversal. This continuation is absent for past winners with low Stock Information Demand.
    • Stocks with low Stock Information Demand that have decreased in price over the last four weeks exhibit a weak tendency to continue declining over many weeks.
  • Shorter and longer past return measurement intervals and different sorting thresholds yield similar results, alleviating concern about data snooping bias.
  • The sample of stocks is modest and skewed toward firms with large market capitalization. The sample period is short, not accommodating measurement of momentum effects for commonly used past return intervals.

In summary, evidence from limited tests suggests that online search activity may help identify which recent winning and losing stocks exhibit some tendency to continue winning and losing.

Market Indicators guide

More on sentiment

  • Testing a Proxy for the Goldman Sachs Panic Index Premium Claude-estimated Goldman Sachs Panic Index values (pixel-reconstructed from a chart) showed high readings (above 8) followed by 1.2% average next-week S&P 500 returns vs…
  • AI-simulated CFO Sentiment Premium GPT-5.4-simulated CFO optimism correlates with actual Duke-Federal Reserve CFO Survey responses (LLM mean 56.6 vs actual 60.1; regression coefficient over six standard errors from…
  • CFO U.S. Economic Sentiment and Stock Market Returns Premium CFO average U.S. economic sentiment shows little ability to predict S&P 500 returns; correlations with next-four-quarter returns are very weak and negative, while change…
  • How Are Sentiment-driven ETFs Doing? Premium An equal-weighted average of three sentiment ETFs (BUZZ, MOOD, NEWZ; monthly rebalanced) underperformed VTI (1.0% vs 10.7% CAGR; MaxDD -51% vs -25%; sample periods…
  • Goldman Sachs Panic Index Proxy Premium A VIX-percentile Panic Index Proxy (trailing 2-year rank, 0–100) shows weak lead-lag association with daily S&P 500 returns, with very high and very low…

All 309 articles in the Market Indicators guide