Search Engine Users Research Articles

Gravizor

Users of Web search engines are generally confronted to numerous responses that are rarely structured, making it difficult to analyze the available results. Indeed, the linear results displayed through lists ordered according to a relevance criterion, although still widely used, seem often limitless. A solution to this problem is to improve the interfaces for better visualization of large number of results. In this paper, we propose modeling and implementation of a tool for graphical visualization and manipulation of results returned by search engines. The goal is to facilitate the analysis, the interpretation and the supervision of users' information needs. The architecture of the ‘Gravisor' tool is based on Multi-Agent paradigm. It is composed of four agents working in full cooperation and coordination. We hope that besides the web information retrieval field, the three graphical visualization modes offered by the ‘Gravisor' tool will be a promising alternative for better information visualization in other areas.

The best privacy defense is a good privacy offense: obfuscating a search engine user’s profile

User privacy on the internet is an important and unsolved problem. So far, no sufficient and comprehensive solution has been proposed that helps a user to protect his or her privacy while using the internet. Data are collected and assembled by numerous service providers. Solutions so far focused on the side of the service providers to store encrypted or transformed data that can be still used for analysis. This has a major flaw, as it relies on the service providers to do this. The user has no chance of actively protecting his or her privacy. In this work, we suggest a new approach, empowering the user to take advantage of the same tool the other side has, namely data mining to produce data which obfuscates the user’s profile. We apply this approach to search engine queries and use feedback of the search engines in terms of personalized advertisements in an algorithm similar to reinforcement learning to generate new queries potentially confusing the search engine. We evaluated the approach using a real-world data set. While evaluation is hard, we achieve results that indicate that it is possible to influence the user’s profile that the search engine generates. This shows that it is feasible to defend a user’s privacy from a new and more practical perspective.

The effects of credibility cues on the selection of search engine results

Web search engines act as gatekeepers when people search for information online. Research has shown that search engine users seem to trust the search engines' ranking uncritically and mostly select top‐ranked results. This study further examines search engine users' selection behavior. Drawing from the credibility and information research literature, we test whether the presence or absence of certain credibility cues influences the selection probability of search engine results. In an observational study, participants (N = 247) completed two information research tasks on preset search engine results pages, on which three credibility cues (source reputation, message neutrality, and social recommendations) as well as the search result ranking were systematically varied. The results of our study confirm the significance of the ranking. Of the three credibility cues, only reputation had an additional effect on selection probabilities. Personal characteristics (prior knowledge about the researched issues, search engine usage patterns, etc.) did not influence the preference for search results linked with certain credibility cues. These findings are discussed in light of situational and contextual characteristics (e.g., involvement, low‐cost scenarios).

Periodicity in User Engagement with a Search Engine and Its Application to Online Controlled Experiments

Nowadays, billions of people use the Web in connection with their daily needs. A significant part of these needs are constituted by search tasks that are usually addressed by search engines. Thus, daily search needs result in regular user engagement with a search engine. User engagement with web services was studied in various aspects, but there appears to be little work devoted to its regularity and periodicity. In this article, we study periodicity of user engagement with a popular search engine through applying spectrum analysis to temporal sequences of different engagement metrics. First, we found periodicity patterns of user engagement and revealed classes of users whose periodicity patterns do not change over a long period of time. In addition, we give an exhaustive analysis of the stability and quality of identified clusters. Second, we used the spectrum series as key metrics to evaluate search quality. We found that the novel periodicity metrics outperform the state-of-the-art quality metrics both in terms of significance level ( p -value) and sensitivity to a large set of larges-scale A/B experiments conducted on real search engine users.

The Computational Turn in Social Sciences. Challenges of the New Empiricism in the Age of Big Data

Today large amounts of data are available to use for research on human behaviour: social media, data from online social networks, vast amounts of digital text, sensory information from personal hand-held and other devices, information from search engine usage and other online services, etc. The industry that relies on collecting, combining, selling and analysing digital footprints for all kinds of purposes ranging from simple targeted advertising to risk assessments and mass surveillance is developing with lightning speed. (Van Es and Schafer, 2017). However, such data could increasingly be used to address larger societal issues of social interactions and relations, inequality, education, healthcare, political participation, and more. The advances in the use of such data in social sciences offer the possibility to answer questions that were beyond research in the past, and this new generation of large-scale, complex, and usually unstructured data requires new forms of data analysis and scientific applications. Some also suggest that as a consequence of the data revolution that we are already living in, a major paradigm shift in science is expected with far-reaching consequences to how research is conducted and knowledge is produced (Mayer-Schonberger and Cukier, 2013; Meyer and Schroeder, 2015). While the course of development in the data-driven industries and research seems to be unambiguous for the future in terms of its expected impact on business and how societies function in general, today the possibilities are still frequently overestimated by some ‘positivistic prophets’ – coming mostly from outside academia. In addition to presenting the main arguments of the papers in this section, the purpose of this editorial is to highlight a few of those issues and challenges that may shape the future of social sciences and of those who pursue in it, in relation to the new data landscape. After briefly elaborating on the definitions of Big Data, the focus will move to the question of epistemology; the changing dynamics among various fields of sciences; the new divides in access to data; and the main ideas behind the critical approach that social sciences might follow to find their right place in the puzzle.

Use of ResearchGate and Google CSE for author name disambiguation

Author name disambiguation plays a very important role in individual based bibliometric analysis and has suffered from lack of information. Therefore, some have tried to leverage external web sources to obtain additional evidence with success. However, the main problem is generally the high cost of extracting data from web pages due to their diverse designs. Considering this challenge, we employed ResearchGate (RG), a social network platform for scholars presenting their publication lists in a structured way. Even though the platform might be imperfect, it can be valuable when it is used along with traditional approaches for the purpose of confirmation. To this end, in our first (retrieval) stage we applied a graph based machine learning approach, connected components (CC) and formed clusters. Then, the data crawled from RG for the same authors were combined with the CC results in stage 2. We observed that 76.40% of the clusters formed by CC were confirmed by the RG data and they accounted for 68.33% of all citations. Second, a subset was drawn from the dataset by retaining those clusters having at least 10 members to examine the details. This time we additionally employed the Google Custom Search Engine (CSE) API to access authors' web pages as a complementary tool to RG. We observed an F score of 0.95 when CC results were confirmed by RG&CSE. Almost the same success was observed when only the CC approach was applied. In addition, we observed that the publications identified and confirmed through the external sources were cited to a greater extent than those publications not found in the related external sources. Even though promising, there are still issues with the use of external sources. We have seen that many authors present only a few selected papers on the web. This hampers our procedure, making it unable to obtain the entire publication list. Missing publications affect bibliometric analysis adversely since all citation data is required. That is, if only the data confirmed via external sources is used, bibliometric indicators will be overestimated. On the other hand, our suggested methodology can potentially decrease the manual work required for individual based bibliometric analysis. The procedure may also present more reliable results by confirming cluster members derived from unsupervised grouping methods. This approach might be especially beneficial for large datasets where extensive manual work would otherwise be required.

Examining Guidelines for School-Based Breakfast Programs in Canada: A Systematic Review of the Grey Literature.

School breakfast programs are widespread and serve varying objectives regarding youth health promotion. Evidence-based guidelines for breakfast programs may be important in maximizing their effectiveness related to student outcomes, yet it is unclear what is available in Canada. A systematic review was conducted to identify and compare Canadian guidelines related to breakfast programs. Data sources included grey literature databases, customized search engines, targeted websites, and content expert consultations. Eligible guidelines met the following criteria: government and nongovernment sources at the federal and provincial/territorial levels, current version, and intended for program coordinators. Recommendations for program delivery were extracted, categorized, and mapped onto the 4 environments outlined in the ANGELO framework, and they were classified as "common" or "inconsistent" across guidelines. Fifteen sets of guidelines were included. No guidelines were available from federal or territorial governments and 4 provincial governments. There were few references to peer-reviewed literature within the guidelines and despite many common recommendations for program delivery, conflicting recommendations were also identified. Potential barriers to program participation, including a lack of consideration of allergies and other dietary restrictions, were identified. Future research should identify how guidelines are implemented and evaluate what effect their implementation has on program delivery and student outcomes.

A Novel Bipartite Graph Based Competitiveness Degree Analysis from Query Logs

Competitiveness degree analysis is a focal point of business strategy and competitive intelligence, aimed to help managers closely monitor to what extent their rivals are competing with them. This article proposes a novel method, namely BCQ, to measure the competitiveness degree between peers from query logs as an important form of user generated contents, which reflects the “wisdom of crowds” from the search engine users’ perspective. In doing so, a bipartite graph model is developed to capture the competitive relationships through conjoint attributes hidden in query logs, where the notion of competitiveness degree for entity pairs is introduced, and then used to identify the competitive paths mapped in the bipartite graph. Subsequently, extensive experiments are conducted to demonstrate the effectiveness of BCQ to quantify the competitiveness degrees. Experimental results reveal that BCQ can well support competitors ranking, which is helpful for devising competitive strategies and pursuing market performance. In addition, efficiency experiments on synthetic data show a good scalability of BCQ on large scale of query logs.

Web-Based Antismoking Advertising to Promote Smoking Cessation: A Randomized Controlled Trial.

BackgroundAlthough hundreds of millions of dollars are spent each year on public health advertising, the advertisement content, design, and placement are usually developed by intuition rather than research.ObjectiveThe objective of our study was to develop a methodology for testing Web-based advertisements to promote smoking cessation.MethodsWe developed 10 advertisements that varied by their content (those that empower viewers to quit, help viewers to quit, or discuss the effects of smoking). We then conducted a series of Web-based randomized controlled trials that explored the effects of exposing users of Microsoft’s Bing search engine to antismoking advertisements that differed by content, placement, or other characteristics. Finally, we followed users to explore whether they conducted subsequent searches for smoking cessation products or services.ResultsThe advertisements were shown 710,106 times and clicked on 1167 times. In general, empowering advertisements had the greatest impact (hazard ratio [HR] 2.6, standard error [SE] 0.09 relative to nonempowering advertisements), but we observed significant variations by gender. For instance, we found that men exposed to smoking cessation advertisements were less likely than women to subsequently conduct smoking cessation searches (HR 0.2, SE 0.07), but that this likelihood increased 3.5 times in men exposed to advertisements containing empowering content. Women were more influenced by advertisements that emphasized the health effects of smoking. We also found that appearing at the top right of the page (HR 2.1, SE 0.07) or at the bottom rather than the top of a list (HR 1.1, SE 0.02) can improve smoking cessation advertisements’ effectiveness in prompting future searches related to smoking cessation.ConclusionsAdvertising should be targeted to different demographic groups in ways that are not always intuitive. Our study provides a method for testing the effectiveness of Web-based antismoking advertisements and demonstrates the importance of advertisements that are tailored according to specific demographics.

Re-ranking Google search returned web documents using document classification scores

Web document ranking is a very challenging issue for search engines because about 80% of the search engine users are usuallyinterested in the top three returned search results only. This paper proposes an effective method for re-ranking Google searchreturned web documents/pages based on document classification. This method downgrades some web documents/pages thathave lower classification scores or been classified into categories irrelevant to the query. The experimental results show thatthe re-ranking of Google search returned web documents using document classification scores can significantly improve theranking performance in terms of the integrated evaluation result using three criteria: MAP, nDCG, and P@20. It is evident thatthe proposed re-ranking method can meet the user’s information need better.

Examining the themes of STD-related Internet searches to increase specificity of disease forecasting using Internet search terms.

US surveillance of sexually transmitted diseases (STDs) is often delayed and incomplete which creates missed opportunities to identify and respond to trends in disease. Internet search engine data has the potential to be an efficient, economical and representative enhancement to the established surveillance system. Google Trends allows the download of de-identified search engine data, which has been used to demonstrate the positive and statistically significant association between STD-related search terms and STD rates. In this study, search engine user content was identified by surveying specific exposure groups of individuals (STD clinic patients and university students) aged 18–35. Participants were asked to list the terms they use to search for STD-related information. Google Correlate was used to validate search term content. On average STD clinic participant queries were longer compared to student queries. STD clinic participants were more likely to report using search terms that were related to symptomatology such as describing symptoms of STDs, while students were more likely to report searching for general information. These differences in search terms by subpopulation have implications for STD surveillance in populations at most risk for disease acquisition.

Impact of Predicting Health Care Utilization Via Web Search Behavior: A Data-Driven Analysis.

BackgroundBy recent estimates, the steady rise in health care costs has deprived more than 45 million Americans of health care services and has encouraged health care providers to better understand the key drivers of health care utilization from a population health management perspective. Prior studies suggest the feasibility of mining population-level patterns of health care resource utilization from observational analysis of Internet search logs; however, the utility of the endeavor to the various stakeholders in a health ecosystem remains unclear.ObjectiveThe aim was to carry out a closed-loop evaluation of the utility of health care use predictions using the conversion rates of advertisements that were displayed to the predicted future utilizers as a surrogate. The statistical models to predict the probability of user’s future visit to a medical facility were built using effective predictors of health care resource utilization, extracted from a deidentified dataset of geotagged mobile Internet search logs representing searches made by users of the Baidu search engine between March 2015 and May 2015.MethodsWe inferred presence within the geofence of a medical facility from location and duration information from users’ search logs and putatively assigned medical facility visit labels to qualifying search logs. We constructed a matrix of general, semantic, and location-based features from search logs of users that had 42 or more search days preceding a medical facility visit as well as from search logs of users that had no medical visits and trained statistical learners for predicting future medical visits. We then carried out a closed-loop evaluation of the utility of health care use predictions using the show conversion rates of advertisements displayed to the predicted future utilizers. In the context of behaviorally targeted advertising, wherein health care providers are interested in minimizing their cost per conversion, the association between show conversion rate and predicted utilization score, served as a surrogate measure of the model’s utility.ResultsWe obtained the highest area under the curve (0.796) in medical visit prediction with our random forests model and daywise features. Ablating feature categories one at a time showed that the model performance worsened the most when location features were dropped. An online evaluation in which advertisements were served to users who had a high predicted probability of a future medical visit showed a 3.96% increase in the show conversion rate.ConclusionsResults from our experiments done in a research setting suggest that it is possible to accurately predict future patient visits from geotagged mobile search logs. Results from the offline and online experiments on the utility of health utilization predictions suggest that such prediction can have utility for health care providers.

Inference of User Image-Search Goals and Personalization Using Click Through Log

Improving the image search engine relevance and user experience is very important to figure out user image search goals. When a user will enter a query to search an image, he should be displayed with relevant images. In proposed work, browsing history session information, bookmark data and visual information with image tags of user click through images or user feedback images are extracted. The session history is stored as click through log and the images are stored separately. This history and clicked and downloaded images by user is considered as implicit guidance, so that the personalized results can be presented to the user. From the browsing history, the URLs are visited for getting user domain keywords. By using these keywords and tags of images, user query specific topic mapping and query mapping is done. The proposed method performs Naive Bayesian classification on user clicked images to group them into relevant concepts. This classifier is tested on the images obtained as a result of user submitted, so that the user interesting images or goal images can be displayed as a result. A label wise clustering is used to display goal image results. The system is mainly for retrieving images using text-based queries. The main aim of the proposed work is an efficient image retrieval system to facilitates image search through user queries and improve user satisfaction by returning images that have a high probability to be downloaded by the user. Index Terms—Click through log, User Profiles, Goal images, Image search goals.

Improving the freshness of the search engines by a probabilistic approach based incremental crawler

Web is flooded with data. While the crawler is responsible for accessing these web pages and giving it to the indexer for making them available to the users of search engine, the rate at which these web pages change has created the necessity for the crawler to employ refresh strategies to give updated/modified content to the search engine users. Furthermore, Deep web is that part of the web that has alarmingly abundant amounts of quality data (when compared to normal/surface web) but not technically accessible to a search engine’s crawler. The existing deep web crawl methods helps to access the deep web data from the result pages that are generated by filling forms with a set of queries and accessing the web databases through them. However, these methods suffer from not being able to maintain the freshness of the local databases. Both the surface web and the deep web needs an incremental crawl associated with the normal crawl architecture to overcome this problem. Crawling the deep web requires the selection of an appropriate set of queries so that they can cover almost all the records in the data source and in addition the overlapping of records should be low so that network utilization is reduced. An incremental crawl adds to an increase in the network utilization with every increment. Therefore, a reduced query set as described earlier should be used in order to minimize the network utilization. Our contributions in this work are the design of a probabilistic approach based incremental crawler to handle the dynamic changes of the surface web pages, adapting the above mentioned method with a modification to handle the dynamic changes in the deep web databases, a new evaluation measure called the ‘Crawl-hit rate’ to evaluate the efficiency of the incremental crawler in terms of the number of times the crawl is actually necessary in the predicted time and a semantic weighted set covering algorithm for reducing the queries so that the network cost is reduced for every increment of the crawl without any compromise in the number of records retrieved. The evaluation of incremental crawler shows a good improvement in the freshness of the databases and a good Crawl-hit rate (83 % for web pages and 81 % for deep web databases) with a lesser over head when compared to the baseline.

Prefix-Adaptive and Time-Sensitive Personalized Query Auto Completion

Query auto completion (QAC) methods recommend queries to search engine users when they start entering a query. Current QAC methods mostly rank query completions based on their past popularity, i.e., on the number of times they have previously been submitted as a query. However, query popularity changes over time and may vary drastically across users. Accordingly, the ranking of query completions should be adjusted. Previous time-sensitive and user-specific QAC methods have been developed separately, yielding significant improvements over methods that are neither time-sensitive nor personalized. We propose a hybrid QAC method that is both time-sensitive and personalized. We extend it to handle long-tail prefixes, which we achieve by assigning optimal weights to the contribution from time-sensitivity and personalization. Using real-world search log datasets, we return top <inline-formula><tex-math notation="LaTeX"> $N$</tex-math> </inline-formula> query suggestions ranked by predicted popularity as estimated from popularity trends and cyclic popularity behavior; we rerank them by integrating similarities to a user's previous queries (both in the current session and in previous sessions). Our method outperforms state-of-the-art time-sensitive QAC baselines, achieving total improvements of between 3 and 7 percent in terms of mean reciprocal rank (MRR). After optimizing the weights, our extended model achieves MRR improvements of between 4 and 8 percent.

Search Engine Behavior and Satisfaction:A Survey-Based Study among Users in Malaysia

The birth of the internet in the 1990‟s did not only change the way of how people communicate but also of how they access information. The amount of information that the internet offers is enormous, it grows by the day and can be retrieved at any time – only technical issues may interrupt its constant availability. That is why the World Wide Web is nowadays the first port for information retrieval. Information retrieval tools are indispensible in this environment. They filter the information mass and allow users to locate the desired information.Search engines are one of the most popular web services.Most of what is known about user search engine behavior comes from query log analysis and clickthrough analysis. Only few studies have so far examined search engine behavior and user satisfaction from a mere user perspective.The number still shrinks when it comes to narrowing down the research focus on users of a specific country or language community. This study investigates user search engine behavior and satisfaction from the perspective of Chinese-speaking users in Malaysia. A survey made among 62 Malaysian Chinese users assesses search engine usage frequency, preferred search engines, and user priorities for search engine selection. It also assesses linguistic aspects such as preferred search language and search engine interface language. The study evaluates the users‟ satisfaction with the search results in general and the search results on the first page, with the search results of English and Chinese search queries, andthe necessity for query rephrasing. Where possible, the study compares the results with existing studies conducted in Malaysia.

Measuring and Predicting Search Engine Users’ Satisfaction

Search satisfaction is defined as the fulfillment of a user’s information need. Characterizing and predicting the satisfaction of search engine users is vital for improving ranking models, increasing user retention rates, and growing market share. This article provides an overview of the research areas related to user satisfaction. First, we show that whenever users choose to defect from one search engine to another they do so mostly due to dissatisfaction with the search results. We also describe several search engine switching prediction methods, which could help search engines retain more users. Second, we discuss research on the difference between good and bad abandonment, which shows that in approximately 30% of all abandoned searches the users are in fact satisfied with the results. Third, we catalog techniques to determine queries and groups of queries that are underperforming in terms of user satisfaction. This can help improve search engines by developing specialized rankers for these query patterns. Fourth, we detail how task difficulty affects user behavior and how task difficulty can be predicted. Fifth, we characterize satisfaction and we compare major satisfaction prediction algorithms.

Search Engines that Learn from Their Users

More than half the world's population uses web search engines, resulting in over half a billion queries every single day. For many people, web search engines such as Baidu, Bing, Google, and Yandex are among the first resources they go to when a question arises. Moreover, for many search engines have become the most trusted route to information, more so even than traditional media such as newspapers, news websites or news channels on television. What web search engines present people with greatly influences what they believe to be true and consequently it influences their thoughts, opinions, decisions, and the actions they take. With this in mind two things are important, from an information retrieval research perspective. First, it is important to understand how well search engines (rankers) perform and secondly this knowledge should be used to improve them. This thesis is about these two topics: evaluation of search engines and learning search engines. In the first part of this thesis we investigate how user interactions with search engines can be used to evaluate search engines. In particular, we introduce a new online evaluation paradigm called multileaving that extends upon interleaving. With multileaving, many rankers can be compared at once by combining document lists from these rankers into a single result list and attributing user interactions with this list to the rankers. Then we investigate the relation between A/B testing and interleaved comparison methods. Both studies lead to much higher sensitivity of the evaluation methods, meaning that fewer user interactions are required to arrive at reliable conclusions. This has the important implication that fewer users need to be exposed to the results from possibly inferior search engines. In the second part of this thesis we turn to online learning to rank. We learn from the evaluation methods introduced and extended upon in the first part. We learn the parameters of base rankers based on user interactions. Then we use the multileaving methods as feedback in our learning method, leading to much faster convergence than existing methods. Again, the important implication is that fewer users need to be exposed to possibly inferior search engines as they adapt more quickly to changes in user preferences. The last part of this thesis is of a different nature than the earlier two parts. As opposed to the earlier chapters, we no longer study algorithms. Progress in information retrieval research has always been driven by a combination of algorithms, shared resources, and evaluation. In the last part we focus on the latter two. We introduce a new shared resource and a new evaluation paradigm. Firstly, we propose Lerot. Lerot is an online evaluation framework that allows us to simulate users interacting with a search engine. Our implementation has been released as open source software and is currently being used by researchers around the world. Secondly we introduce OpenSearch, a new evaluation paradigm involving real users of real search engines. We describe an implementation of this paradigm that has already been widely adopted by the research community through challenges at CLEF and TREC.

A novel trend surveillance system using the information from web search engines

Web search engines are becoming a major platform for the general public to access information. It has been suggested that because the search patterns of search engine users are correlated with emerging events, the query log of search engines has the potential for trend surveillance, such as monitoring outbreaks of epidemics. Many trend surveillance studies have investigated the use of query logs and have strived to identify query terms suitable for trend surveillance. Most of these works select representative query terms by consulting domain experts or by preparing a large text corpus for feature selection. The process of these approaches, however, is too costly to make the trend surveillance methods adaptable to different topics. In this paper, we propose an adaptive trend surveillance method. We developed a simple and effective feature selection algorithm, called TF-LTR, which leverages the document returned by search engines and the frequency of the terms in the returned documents to select representative query terms of trending topics. Specifically, we investigated pair-wise learning to rank models in order to measure a term's discriminative power in making a document rank higher in the returned document list. The discriminative power is combined with the term frequency which denotes the on-topic degree of a term to measure a term's representativeness against a trending topic. Representative terms and their query frequencies are applied to a state-of-the-art data mining model to enhance the effectiveness of trend surveillance. The experimental results based on trending topics of different domains show that our trend surveillance method performs well and the ranking information of search engines are helpful for trend surveillance. In light of this, the proposed method can provide effective support for government officials and authorities in order to help them to respond to fast-changing events and topics, and to make appropriate decisions.

Analysis of Search Engine Optimization Algorithm

SEO stands for engine optimization. It is the process of getting traffic from the free, organic, editorial or natural search results on search engines. The earlier (or higher ranked on the search results page), and more frequently a site appears in the search results list, the more visitors it will receive from the search engine's users, and these visitors can be converted into customers. SEO may target different kinds of search, including image search, local search, video search, academic search, news search and industry-specific vertical search engines. As an Internet marketing strategy, SEO considers how search engines work, what people search for, the actual search terms or keywords typed into search engines and which search engines are preferred by their targeted audience. Optimizing a website may involve editing its content, HTML and associated coding to both increase its relevance to specific keywords and to remove barriers to the indexing activities of search engines. Promoting a site to increase the number of backlinks, or inbound links, is another SEO tactic. As of May 2015, mobile search has finally surpassed desktop search, Google is developing and pushing mobile search as the future in all of its products and many brands are beginning to take a different approach on their internet strategies.