Does More Context Help? Effects of Context Window and Application Source on Retrieval Performance

We study the effect of contextual information obtained from a user’s digital trace on Web search performance. Contextual information is modeled using Dirichlet–Hawkes processes (DHP) and used in augmenting Web search queries. The context is captured by monitoring all naturally occurring user behavior using continuous 24/7 recordings of the screen and associating the context with the queries issued by the users. We report a field study in which 13 participants installed a screen recording and digital activity monitoring system on their laptops for 14 days, resulting in data on all Web search queries and the associated context data. A query augmentation (QAug) model was built to expand the original query with semantically related terms. The effects of context window and source were determined by training context models with temporally varying context windows and varying application sources. The context models were then utilized to re-rank the QAug model. We evaluate the context models by using the Web document rankings of the original query as a control condition compared against various experimental conditions: (1) a search context condition in which the context was sourced from search history; (2) a non-search context condition in which the context was sourced from all interactions excluding search history; (3) a comprehensive context condition in which the context was sourced from both search and non-search histories; and (4) an application-specific condition in which the context was sourced from interaction histories captured on a specific application type. Our results indicated that incorporating more contextual information significantly improved Web search rankings as measured by the positions of the documents on which users clicked in the search result pages. The effects and importance of different context windows and application sources, along with different query types are analyzed, and their impact on Web search performance is discussed.

Mass Media as a Mirror of the COVID-19 Pandemic

The media plays an important role in disseminating facts and knowledge to the public at critical times, and the COVID-19 pandemic is a good example of such a period. This research is devoted to performing a comparative analysis of the representation of topics connected with the pandemic in the internet media of Kazakhstan and the Russian Federation. The main goal of the research is to propose a method that would make it possible to analyze the correlation between mass media dynamic indicators and the World Health Organization COVID-19 data. In order to solve the task, three approaches related to the representation of mass media dynamics in numerical form—automatically obtained topics, average sentiment, and dynamic indicators—were proposed and applied according to a manually selected list of search queries. The results of the analysis indicate similarities and differences in the ways in which the epidemiological situation is reflected in publications in Russia and in Kazakhstan. In particular, the publication activity in both countries correlates with the absolute indicators, such as the daily number of new infections, and the daily number of deaths. However, mass media tend to ignore the positive rate of confirmed cases and the virus reproduction rate. If we consider strictness of quarantine measures, mass media in Russia show a rather high correlation, while in Kazakhstan, the correlation is much lower. Analysis of search queries revealed that in Kazakhstan the problem of fake news and disinformation is more acute during periods of deterioration of the epidemiological situation, when the level of crime and poverty increase. The novelty of this work is the proposal and implementation of a method that allows the performing of a comparative analysis of objective COVID-19 statistics and several mass media indicators. In addition, it is the first time that such a comparative analysis, between different countries, has been performed on a corpus in a language other than English.

Long Short-Term Memory Network for Predicting Exchange Rate of the Ghanaian Cedi

An accurate prediction of the Exchange Rate (ER) serves as the basis for effective financial management, monetary policies, and long-term strategic decision making worldwide. A stable and competitive ER enables economic diversification. Economists, researchers, and investors have conducted several studies to predict trends and facts that influence the ER’s rise or fall. This paper used the Long Short-Term Memory Networks (LSTM) framework to predict the weekly exchange rate of one Ghanaian Cedis (GH₵) to three different currencies (United States Dollar, British Pound, and Euro), using Google Trends and historical macroeconomic data. We fused past exchange rates, fundamental macroeconomic variables, commodity prices (cocoa, gold, and crude oil) and public search queries (Google Trends) as input parameters. An empirical analysis using publicly available ER data from the Bank of Ghana (BoG) from January 2004 to October 2019 showed satisfactory results. We observed that the proposed LSTM model outperformed the Support Vector Regressor (SVR) and Back-propagation Neural Network (BPNN) models in accuracy and closeness metrics. That is, our LSTM model obtained (MAE = 0.033, MSE = 0.0035, RMSE = 0.0551, R2 = 0.9983, RMSLE = 0.0129 and MAPE = 0.0121) compared with SVR (MAE = 0.05, MAE = 0.005, RMSE = 0.0683, R2 = 0.9973, RMSLE = 0.0191 and MAPE = 0.0241) and BPNN (MAE = 0.04, MAE = 0.0056, RMSE = 0.0688, R2 = 0.9974, RMSLE = 0.0172 and MAPE = 0.0168). Moreover, we observed a strong positive correction (0.98–0.99) between Google Trends on the currency of focus and its exchange rate to the Ghanaian cedis. The study results show the importance of incorporating public search queries from search engines to predict the ER accurately.

Cultural Health Moments: A Search Analysis During Times of Heightened Awareness to Identify Potential Interception Points with Digital Health Consumers

Year after year whenever someone who is considered “high profile” discovers that they have some sort of sickness or if they pass away due to a sickness, there seems to be a heightened interest in that person. At the same time however, there is a heightened awareness of the type of sickness that the person had. Finding the moments in which there is a heightened sense of awareness towards a specific topic can be something of high value to various agencies and organizations. The objective of this study was to explore the moments in which people start to do some initial search queries when there is a high-profile health moment. Once it is understood when this moment occurs, further research can be done to understand where the search behavior shifts to searches of awareness, signs, symptoms, and introspection over time.

Use and E ffect of Google Ads Effect of Google Ads for M arketing S uccess

The present article examines success factors by using and implementing google ads in enterprises. In order to assess the importance of google ads for marketing success, the first step is to classify the importance of google as a search platform. Measured in terms of page views, google was the clear market leader in the search engine market with a market share of 87.66 percent, ahead of Bing and Yahoo. 5.8 billion search queries per day - two trillion search queries per year - also generate opportunities for companies to present themselves and win customers. The results of this research suggest that the keyword for successful online marketing in SEA focuses on relevance. Only if content is created that, in addition to the actual promotion of a product or service, leads to further and for the user target-oriented information, the campaign experiences a quality upgrade, which not only affects the ranking and quality factors, but also the conversion behavior of customers. Based on the execution of a literature review, which has been carried out with emphasis on empirical studies and essays since 2010, four main success factors, such as presentation and content of the website, accordingly keyword marketing, the complementary use of analytics, and ad extension have been evolved.

Mental Health Interest and Its Prediction during the COVID-19 Pandemic Using Google Trends

This study aimed to analyze and predict interest in mental health-related queries created in Google Trends (GT) during the COVID-19 pandemic. The Google Trends tool collected data on the Google search engine interest and provided real-time surveillance. Five key phrases: “depression”, “insomnia”, ”loneliness”, “psychologist”, and “psychiatrist”, were studied for the period from 25 September 2016 to 19 September 2021. The predictions for the upcoming trend were carried out for the period from September 2021 to September 2023 and were estimated by a hybrid five-component model. The results show a decrease of interest in the search queries “depression” and “loneliness” by 15.3% and 7.2%, respectively. Compared to the period under review, an increase of 5.2% in “insomnia” expression and 8.4% in the “psychiatrist” phrase were predicted. The expression “psychologist” is expected to show an almost unchanged interest. The upcoming changes in the expressions connected with mental health might be explained by vaccination and the gradual removal of social distancing rules. Finally, the analysis of GT can provide a timely insight into the mental health interest of a population and give a forecast for a short period trend.

Consumer behavior in the digital environment under the influence of the COVID-19 pandemic: the importance of the health factor and business transparency

Introduction. With the onset of quarantine caused by the COVID-19 pandemic, changes in consumer behavior are evident, such as increased panic and more conscious behavior focusing on health and avoiding potential threats. Therefore, the study of consumer behavior in such conditions is an urgent and timely task.Purpose. The study aims to analyze changes in consumer behavior in the digital environment under the influence of events caused by the COVID-19 pandemic.Method (methodology). The theoretical and methodological basis of the study were general scientific methods of scientific knowledge: theoretical generalization, systematization, analysis and synthesis. The authors investigated trends in consumer behavior in the context of the COVID-19 pandemic. The main stages of change in consumer behavior are analyzed. The steps of the transition of companies to communicate with consumers in the digital environment were singled out. Factors such as health care and openness (business transparency) have been identified as determinants of trust in businesses in times of crisis. Brief statistics on the global consumption of products in various fields are presented. In particular, the positive dynamics in the growth of Internet users’ search queries for the purchase of health products are revealed. A comparison of the number of search queries in the Google Trends service for thematic terms of the research: «product delivery» and «health» within the Ukrainian market and in the world. It is determined that a new direction of word-of-mouth marketing is gaining popularity, which is an effective tool for communication with consumers in the digital environment through social networks and various cyberspace sites. Results. The authors identify the main trends in Internet marketing in recent years and make recommendations on marketing tools for future strategies of companies in the digital environment. The findings can be helpful to experts in the field of product promotion on the Internet and practicing marketers in the area of innovative services, which are gaining popularity in the wake of global trends in consumer behavior.Perspectives. In further research, the authors should focus on quantitative marketing research of consumers’ attitudes to companies’ product offerings and their willingness to cooperate, supported by the developed marketing programs.

APPLYING NORMS, WEIGHTS AND MEASURES AS A QUERY SEARCH METHOD

В статье рассматривается возможность применения распределения потоков информации при работе в средах систем управления базами данных. Особое внимание уделяется использованию норм для дополнительной оптимизации последовательности поисковых запросов к массивам данных большого объема. In the article, the possibilities of distributing information flows when working in environments of database management systems. Particular attention is paid to the use of normal methods for optimizing search queries against a large amount of data.

An Evaluation of 5-Year Web Analytics for HeadsUpGuys: A Men’s Depression E-Mental Health Resource

The present study reports an evaluation of web analytics, over a 5-year period, for HeadsUpGuys.org , an eHealth resource for men with depression. Google Analytics, Search Console, and Tag Manager were used to monitor user activity over the course of the website’s first 5 years (June 15, 2015–June 15, 2020). Through this period, HeadsUpGuys had a total of 1,665,356 unique users, amounting to 1,948,481 sessions and 3,328,258 page views. Organic traffic accounted for the highest proportion (53.44%; n = 1,041,277) of website sessions. Four of the top 10 Google search queries that brought users to the website related to suicidality. Three countries (United States, United Kingdom, Canada) accounted for almost three-quarters (71.10%; n = 1,385,485) of the site’s traffic. Nearly three-quarters (73.35%; n = 1,429,285) of sessions occurred on a mobile device. The goal conversion rate for the Self Check was 60.27%. The average time on page was 2 min 53 s, with a bounce rate of 65.92%, and an exit rate of 57.20%. The goal conversion rate for the Stress Test was 52.89%. The average time on page was 4 min 8 s, with a bounce rate of 72.40% and an exit rate of 48.88%. The conversion rate for the final goal was 11.53%, indicating that approximately one in 10 visitors to the site had a session of at least 3 min. The findings illustrate the potential of eHealth resources to support men’s mental health and provide a real-world benchmark to help advance the men’s eHealth field.