Google search based sentiment indexes. Issue 3 (September 2020)

• Record Type: Journal Article
• Authors: Brochado, Ana
• Is Part Of: IIMB management review. Volume 32:Issue 3(2020:Sep.)
• Page Start: 325
• Page End: 335
• Publication Date: 2020-09
• Subjects: Investor sentiment -- Search-based data -- Stock market -- Portugal; Management -- Periodicals; Industrial management -- Periodicals; Industrial management; Management; India; Periodicals; 658
• DOI: 10.1016/j.iimb.2019.10.015
• Languages: English
• ISSNs: 0970-3896

Abstract

Abstract: This study sought to confirm whether Internet search based data have the potential both to reveal populations' underlying beliefs directly and to affect stock markets of countries – in this case, Portugal. Based on the Internet search volume of several queries related to household concerns, we constructed two Google-based sentiment measures – a Positive Sentiment Index and a Negative Sentiment Index – encompassing both positive and negative search terms. The results reveal that both measures are correlated with aggregate stock market returns, trading volume, and abnormal trading volume. Also, positive sentiment has a stronger impact on these stock market variables than negative sentiment. Further, the proposed sentiment measures are significantly useful when making short-term predictions of market returns and volume.