Economics at your fingertips  


Ana Brochado

No 9341, EcoMod2016 from EcoMod

Abstract: As Internet searches are generated by the spontaneous behavior of agents, these search patterns may possess signaling properties. This study tests whether Internet search-based data have the potential both to reveal directly populations’ underlying beliefs and to affect the Portuguese stock market. Based on the Internet search volume of several queries related to household concerns, we construct two Google-based sentiment measures, encompassing both positive and negative search terms (i.e., the Positive Sentiment and Negative Sentiment Indexes). The results reveal that both measures are correlated with aggregate stock market returns, trading volume, and abnormal trading volume. We also find that positive sentiment has a stronger impact on these stock market variables than negative sentiment. Moreover, the results show that these measures are significantly useful in the short-term prediction of market returns and volume. The findings of this study encourage the use of sentiment measures based on search queries, since they are available for shorter periods than other well-known measures of economic sentiment.

Keywords: Portugal; Finance; Modeling: new developments (search for similar items in EconPapers)
Date: 2016-07-04
References: View references in EconPapers View complete reference list from CitEc
Citations Track citations by RSS feed

Downloads: (external link) ... an%20we%20google.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link:

Access Statistics for this paper

More papers in EcoMod2016 from EcoMod Contact information at EDIRC.
Series data maintained by Theresa Leary ().

Page updated 2017-10-13
Handle: RePEc:ekd:009007:9341