We propose an innovative and forward-looking method to examine investor herd behavior and identify fundamental-driven spurious herding. A sentence-based sentiment analysis approach is conceived to automatically extract attitudes or emotions from textual documents. Then we build a mathematical model to discern herd behavior by exploiting the sentiment indices. Empirical tests in the Chinese stock market indicate that there exists significant true herd behavior among blue-chips. Investors with pessimistic sentiment are more likely to herd than those with optimistic sentiment. Moreover, macroeconomic information tends to play a dominant role in the decision-making processes, and the lack of rapid and efficient firm-specific information enables people to herd around the market consensus.