Predicting Human Behavior Based on Web Search Activity: Greek Referendum of 2015

2016 ◽  
pp. 1-7
Author(s):  
Spyros E. Polykalas ◽  
George N. Prezerakos
Keyword(s):  
Human Behavior ◽  
Web Search ◽  
Search Activity ◽  
Behavior Based

scholarly journals Revisiting the use of web search data for stock market movements

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Xu Zhong ◽  
Michael Raghib
Keyword(s):  
Web Search ◽  
Selection Process ◽  
Adaptive Strategy ◽  
Computational Social Science ◽  
Search Activity ◽  
Term Selection ◽  
Search Terms ◽  
Search Data ◽  
Market Trends ◽  
The Cost

Abstract Advances in Big Data make it possible to make short-term forecasts for market trends from previously unexplored sources. Trading strategies were recently developed by exploiting a link between the online search activity of certain terms semantically related to finance and market movements. Here we build on these earlier results by exploring a data-driven strategy which adaptively leverages the Google Correlate service and automatically chooses a new set of search terms for every trading decision. In a backtesting experiment run from 2008 to 2017 we obtained a 499% cumulative return which compares favourably with benchmark strategies. A crowdsourcing exercise reveals that the term selection process preferentially selects highly specific terms semantically related to finance (e.g. Wells Fargo Bank), which may capture the transient interests of investors, but at the cost of a shorter span of validity. The adaptive strategy quickly updates the set of search terms when a better combination is found, leading to more consistent predictability. We anticipate that this adaptive decision framework can be of value not only for financial applications, but also in other areas of computational social science, where linkages between facets of collective human behavior and online searches can be inferred from digital footprint data.

Unsupervised analysis of human behavior based on manifold learning

2009 ◽  
Author(s):  
Yu-Ming Liang ◽  
Sheng-Wen Shih ◽  
Arthur Chun-Chieh Shih ◽  
Hong-Yuan Mark Liao ◽  
Cheng-Chung Lin
Keyword(s):  
Human Behavior ◽  
Manifold Learning ◽  
Unsupervised Analysis ◽  
Behavior Based

Archeological Methods for Reconstructing Human Predation on Terrestrial Vertebrates

2002 ◽  
Vol 8 ◽  
pp. 51-68 ◽  
Author(s):  
Gary Haynes
Keyword(s):  
Case Studies ◽  
Human Behavior ◽  
Meat Eating ◽  
Terrestrial Vertebrates ◽  
Animal Bones ◽  
Behavior Based ◽  
Human Predation ◽  
The Way

Archeological interest in predation ranges from studies of the earliest evidence for human meat-eating, to attempts to understand the fossil record's ambiguity about the meaning of associated animal bones and human artifacts. A number of quantitative measures are used to find the meaningful patterns in archeological assemblages, and taphonomic research has also provided analogs and comparative standards for interpreting human behavior based on the evidence for predation. The most important methods, approaches, and interests are discussed here, using case studies to illustrate the way archeologists have thought about the record of humans as predators.

scholarly journals Correction: Urban networks among Chinese cities along "the Belt and Road": A case of web search activity in cyberspace

PLoS ONE ◽  
2018 ◽  
Vol 13 (4) ◽  
pp. e0196141
Author(s):  
Lu Zhang ◽  
Hongru Du ◽  
Yannan Zhao ◽  
Rongwei Wu ◽  
Xiaolei Zhang
Keyword(s):  
Web Search ◽  
Search Activity ◽  
Chinese Cities ◽  
Urban Networks ◽  
Belt And Road ◽  
The Belt And Road

scholarly journals Simulation and Optimization of Warpage of Fiber Reinforced using Human Behavior Based Optimization

2019 ◽  
Vol 8 (10) ◽  
pp. 296-302
Keyword(s):  
Human Behavior ◽  
Optimization Technique ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Optimization Techniques ◽  
Experimental Result ◽  
Fiber Reinforced ◽  
Simulation And Optimization ◽  
Behavior Based ◽  
Warpage Optimization

Warpage is one of the major defects in injection molding and this affects the quality of the materials. Some techniques are used to minimize the warpage by the changing the parameter settings. The optimization techniques were applied to the parameter to find the optimized value. The popular method in optimizing the parameter is Genetic Algorithm (GA) and this has the limitation of big stochastic components. The main objective of this research is to propose the Human Behavior Based Optimization (HBBO) in the warpage. This method doesn’t have large stochastic and has a fast convergence rate. The orthogonal Array is used to measure the warpage for the different parameter settings. The fiber reinforced component is used to measure the performance of the proposed method. The Back Propagation Neural Network is used to find the relationship between the warpage and other factors. Then optimization technique is applied to find the parameter value. The experimental result of the proposed HBBO method in Warpage optimization is compared with other existing method in warpage optimization. The HBBO method has the warpage of 0.0858 and the GA method has the warpage of 0.0953.

scholarly journals A Utility-Theoretic Approach to Privacy in Online Services

2010 ◽  
Vol 39 ◽  
pp. 633-662 ◽  
Author(s):  
A. Krause ◽  
E. Horvitz
Keyword(s):  
Large Scale ◽  
Web Search ◽  
Personal Information ◽  
Personal Data ◽  
Theoretic Approach ◽  
Search Activity ◽  
Efficient Manner ◽  
Special Knowledge ◽  
Limit Access

Online offerings such as web search, news portals, and e-commerce applications face the challenge of providing high-quality service to a large, heterogeneous user base. Recent efforts have highlighted the potential to improve performance by introducing methods to personalize services based on special knowledge about users and their context. For example, a user's demographics, location, and past search and browsing may be useful in enhancing the results offered in response to web search queries. However, reasonable concerns about privacy by both users, providers, and government agencies acting on behalf of citizens, may limit access by services to such information. We introduce and explore an economics of privacy in personalization, where people can opt to share personal information, in a standing or on-demand manner, in return for expected enhancements in the quality of an online service. We focus on the example of web search and formulate realistic objective functions for search efficacy and privacy. We demonstrate how we can find a provably near-optimal optimization of the utility-privacy tradeoff in an efficient manner. We evaluate our methodology on data drawn from a log of the search activity of volunteer participants. We separately assess users’ preferences about privacy and utility via a large-scale survey, aimed at eliciting preferences about peoples’ willingness to trade the sharing of personal data in returns for gains in search efficiency. We show that a significant level of personalization can be achieved using a relatively small amount of information about users.

scholarly journals COVID-19-Related Web Search Behaviors and Infodemic Attitudes in Italy: Infodemiological Study (Preprint)

2020 ◽  
Author(s):  
Alessandro Rovetta ◽  
Akshaya Srikanth Bhagavathula
Keyword(s):  
Web Search ◽  
Population Level ◽  
Google Trends ◽  
The Novel ◽  
Fake News ◽  
Search Activity ◽  
Campania Region ◽  
Search Volume ◽  
Government Websites ◽  
Novel Coronavirus

BACKGROUND Since the beginning of the novel coronavirus disease (COVID-19) outbreak, fake news and misleading information have circulated worldwide, which can profoundly affect public health communication. OBJECTIVE We investigated online search behavior related to the COVID-19 outbreak and the attitudes of “infodemic monikers” (ie, erroneous information that gives rise to interpretative mistakes, fake news, episodes of racism, etc) circulating in Italy. METHODS By using Google Trends to explore the internet search activity related to COVID-19 from January to March 2020, article titles from the most read newspapers and government websites were mined to investigate the attitudes of infodemic monikers circulating across various regions and cities in Italy. Search volume values and average peak comparison (APC) values were used to analyze the results. RESULTS Keywords such as “novel coronavirus,” “China coronavirus,” “COVID-19,” “2019-nCOV,” and “SARS-COV-2” were the top infodemic and scientific COVID-19 terms trending in Italy. The top five searches related to health were “face masks,” “amuchina” (disinfectant), “symptoms of the novel coronavirus,” “health bulletin,” and “vaccines for coronavirus.” The regions of Umbria and Basilicata recorded a high number of infodemic monikers (APC weighted total >140). Misinformation was widely circulated in the Campania region, and racism-related information was widespread in Umbria and Basilicata. These monikers were frequently searched (APC weighted total >100) in more than 10 major cities in Italy, including Rome. CONCLUSIONS We identified a growing regional and population-level interest in COVID-19 in Italy. The majority of searches were related to amuchina, face masks, health bulletins, and COVID-19 symptoms. Since a large number of infodemic monikers were observed across Italy, we recommend that health agencies use Google Trends to predict human behavior as well as to manage misinformation circulation in Italy.

scholarly journals Web Search Trends of Implementing the Patient Autonomy Act in Taiwan

Healthcare ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 353
Author(s):  
Po-Chin Yang ◽  
Mei-Ju Shih ◽  
Ya-An Liu ◽  
Ya-Chuan Hsu ◽  
Hsiao-Ting Chang ◽  
...  
Keyword(s):  
Patient Autonomy ◽  
Web Search ◽  
Information Sources ◽  
Online Information ◽  
Search Activity ◽  
Activity Data ◽  
Web Resources ◽  
Search Volume ◽  
Advance Care ◽  
Google Search

Background: The Patient Autonomy Act was implemented in Taiwan on 6 January 2019. It is the first patient-oriented act in Taiwan, and also the first special act to completely protect patient autonomy in Asia. Our study aimed to investigate the web resources citizens were able to access on the eve of the implementation of the Patient Autonomy Act in Taiwan. Methods: Patient Autonomy Act-related web resources were searched for by entering 10 related terms individually into the Google search engine in January 2019 and again in April 2019. Search activity data were analyzed using Google Trends. Results: “Advance care planning” and “advance decision” were the most relevant keywords for finding information about the Patient Autonomy Act on the eve of the act’s implementation in Taiwan. The main online information sources were non-governmental websites including news sites and online magazines. The related search volume only increased on the eve of implementation. Conclusions: Even though the Patient Autonomy Act was first published three years before its implementation, the related search volume only increased on the eve of its implementation. Therefore, whether the three-year buffer between its publication and implementation was necessary requires further investigation.

Sign in / Sign up

Export Citation Format

Share Document