Predicting the News of Tomorrow Using Patterns in Web Search Queries

Radinsky, Kira; Davidovich, Sagie; Markovitch, Shaul

doi:10.1109/wiiat.2008.215

Cited by 37 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relevant research has also explored predicting riots [13] and the sales of movie tickets [5,12,18] of human culture evolve [25,25,17]. Other relevant work in search and retrieval has focused correlating logs of queries input to search engines with future events in both traditional media [20] and blogs [1]. Ginsberg et al [10] used queries for predicting H1N1 influenza outbreaks.…”

Section: Related Workmentioning

confidence: 99%

Mining the web to predict future events

Radinsky

Horvitz

2013

Proceedings of the Sixth ACM International Conference on Web Search and Data Mining

Self Cite

152

View full text Add to dashboard Cite

We describe and evaluate methods for learning to forecast forthcoming events of interest from a corpus containing 22 years of news stories. We consider the examples of identifying significant increases in the likelihood of disease outbreaks, deaths, and riots in advance of the occurrence of these events in the world. We provide details of methods and studies, including the automated extraction and generalization of sequences of events from news corpora and multiple web resources. We evaluate the predictive power of the approach on real-world events withheld from the system.

show abstract

Section: Related Workmentioning

confidence: 99%

Mining the web to predict future events

Radinsky

Horvitz

2013

Proceedings of the Sixth ACM International Conference on Web Search and Data Mining

Self Cite

152

View full text Add to dashboard Cite

show abstract

“…Radinsky, Davidovich and Markovitch [21] and Preis, Reith and Stanley [22] examined the use of search data for measuring consumer confidence and Vosen and Schmidt [23] studied consumption and retail sales metrics.…”

Section: Using Google Searches Totals To Predict Social Trendsmentioning

confidence: 99%

Google Searches and Suicide Rates in Spain, 2004-2013: Correlation Study (Preprint)

Jiménez¹,

Germán²,

Ramos³

2018

Preprint

View full text Add to dashboard Cite

BACKGROUND Different studies have suggested that web search data are useful in forecasting several phenomena from the field of economics to epidemiology or health issues. OBJECTIVE This study aimed to (1) evaluate the correlation between suicide rates released by the Spanish National Statistics Institute (INE) and internet search trends in Spain reported by Google Trends (GT) for 57 suicide-related terms representing major known risks of suicide and an analysis of these results using a linear regression model and (2) study the differential association between male and female suicide rates published by the INE and internet searches of these 57 terms. METHODS The study period was from 2004 to 2013. In this study, suicide data were collected from (1) Spain’s INE and (2) local internet search data from GT, both from January 2004 to December 2013. We investigated and validated 57 suicide-related terms already tested in scientific studies before 2015 that would be the best predictors of new suicide cases. We then evaluated the nowcasting effects of a GT search through a cross-correlation analysis and by linear regression of the suicide incidence data with the GT data. RESULTS Suicide rates in Spain in the study period were positively associated (r<-0.2) for the general population with the search volume for 7 terms and negatively for 1 from the 57 terms used in previous studies. Suicide rates for men were found to be significantly different than those of women. The search term, “allergy,” demonstrated a lead effect for new suicide cases (r=0.513; P=.001). The next significant correlating terms for those 57 studied were “antidepressant,” “alcohol abstinence,” “relationship breakup” (r=0.295, P=.001; r=0.295, P=.001; and r=0.268, P=.002, respectively). Significantly different results were obtained for men and women. Search terms that correlate with suicide rates of women are consistent with previous studies, showing that the incidence of depression is higher in women than in men, and showing different gender searching patterns. CONCLUSIONS A better understanding of internet search behavior of both men and women in relation to suicide and related topics may help design effective suicide prevention programs based on information provided by search robots and other big data sources.

show abstract

“…Moreover, researchers have also examined the relationship between query behavior and events [184]. There are algorithms for identifying queries that are related to breaking news and for blending relevant news results into core search results [66,164].…”

Section: Behavioral Dynamicsmentioning

confidence: 99%

Using Contextual Information to Understand Searching and Browsing Behavior

Kiseleva

2015

Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Predicting the News of Tomorrow Using Patterns in Web Search Queries

Cited by 37 publications

References 13 publications

Mining the web to predict future events

Mining the web to predict future events

Google Searches and Suicide Rates in Spain, 2004-2013: Correlation Study (Preprint)

Using Contextual Information to Understand Searching and Browsing Behavior

Contact Info

Product

Resources

About