User Search Queries Research Articles

The algorithm for selecting publications on a given topic considering keyword priorities

The article investigates the problems that exist in existing search engines for scientific publications. The search algorithms used in various search engines for scientific publications are described. The aim of the article is to develop a method for selecting publications on a given topic based on assessing the relevance of keyword sets. A review of the literature that was analyzed during the research is presented. Among the publications studied were materials related to the theory of set similarity, namely the use of the Jacquard coefficient and editing distance. A measure for determining the similarity of keyword sets is presented, which is based on the Jacquard coefficient taking into account the weighting coefficients of keywords. An algorithm is presented that can be used to determine the degree of similarity of publications to a user's search query based on keyword sets with weighting coefficients. The algorithm is based on the measure of similarity presented by us and the editing distance presented by us. The algorithm can be used to rank search results in search engines for scientific publications, as well as to compare the efficiency of different search engines, assess the quality of the results they return. The algorithm can also be used in book and film recommendation systems based on user preferences. The article provides the pseudocode of the algorithm. It is demonstrated on a limited data set how the measure calculated by the algorithm changes depending on the distribution of keyword weights in the user's query and the number of keywords.

Utilizing Ant Colony Optimization for Result Merging in Federated Search

Federated search or distributed information retrieval routes the user's search query to multiple component collections and presents a merged result list in ranked order by comparing the relevance score of each returned result. However, the heterogeneity of the component collections makes it challenging for the central broker to compare these relevance scores while fusing the results into a single ranked list. To address this issue, most existing approaches merge the returned results by converting the document ranks to their ranking scores or downloading the documents and computing their relevance score. However, these approaches are not efficient enough, because the former methods suffer from limited efficacy of result merging due to the negligible number of overlapping documents and the latter are resource intensive. The current paper addresses this problem by proposing a new method that extracts features of both documents and component collections from the available information provided by the collections at query time. Each document and its collection features are exploited together to establish the document relevance score. The ant colony optimization is used for information retrieval to create a merged result list. The experimental results with the TREC 2013 FedWeb dataset demonstrate that the proposed method significantly outperforms the baseline approaches.

Multi-Modal Deep Learning based Metadata Extensions for Video Clipping

General video search and recommendation systems primarily rely on metadata and personal information. Metadata includes file names, keywords, tags, and genres, among others, and is used to describe the video's content. The video platform assesses the relevance of user search queries to the video metadata and presents search results in order of highest relevance. Recommendations are based on videos with metadata judged to be similar to the one the user is currently watching. Most platforms offer search and recommendation services by employing separate algorithms for metadata and personal information. Therefore, metadata plays a vital role in video search. Video service platforms develop various algorithms to provide users with more accurate search results and recommendations. Quantifying video similarity is essential to enhance the accuracy of search results and recommendations. Since content producers primarily provide basic metadata, it can be abused. Additionally, the resemblance between similar video segments may diminish depending on its duration. This paper proposes a metadata expansion model that utilizes object recognition and Speech-to-Text (STT) technology. The model selects key objects by analyzing the frequency of their appearance in the video, extracts audio separately, transcribes it into text, and extracts the script. Scripts are quantified by tokenizing them into words using text-mining techniques. By augmenting metadata with key objects and script tokens, various video content search and recommendation platforms are expected to deliver results closer to user search terms and recommend related content.

Polarization of Turkish Society and Technologies of “Network Revolutions”: The Experience of 2013, the military Coup of 2016 and a Look into the Future

The authors of the article, basing on the structural-functional method of system approach, investigate the long-term confrontation in Turkey between the supporters of national independence (neo-Ottoman system) and integration into the liberal-democratic paradigm of the collective West (secular system). The Taksim-Gezi mass protests in 2013 and the attempted military coup on July 15, 2016 by supporters of Fethullah Gulen (“Feto”) are examined through the prism of the methodology of influencing the “pillars” of the political regime. The tools of mass communication, coordination, and mobilization of the population during the mentioned period are studied. The publication uses content analysis and behavioral analysis of user search queries in Google Trends.
 The successful counteraction of the “neo-Ottoman” system to the challenges of the “secular” camp, internal opposition, as well as the role of R. T. Erdogan in maintaining the balance of power in the country is underlined.
 In conclusion, the author highlights the possible risks to Turkey’s stability in the future, associated with changes in the political situation and the opposition, in case of a change of leadership in the country.
 The study is aimed at developing a methodology for determining the cycles of protest activity and the involvement of the population in these events. This will make it possible to predict the level of stability of the political regime to “network revolutions” and coups d'état.

Applying thesauruses in expanding user search queries: From local use to linked data

The subject search in natural languages is the most difficult one due to phraseological ambiguities. To solve the problem, the information systems mobilize the terms in controlled dictionaries, e. g. thesauruses. The authors examine the classifications, thesauruses, subject headings, normative (authority) files within the context of the open networked space of the Linked Open Data environment (LOD). These links enable to enhance (complement) user queries with the words from other dictionaries, and to navigate through the other libraries’ systems for the resources. The authors explore the possibility of practical application of EUROVOC and GEMET thesauruses to expand search queries initiated by the users of RNPLS&T’s Single Open Information Archive (SOIA), Portal of Electronic Library (PEL) of the Parliamentary Library of the RF Federal Assembly and the thematic database “Ecology: Science and technologies”, which records could be potentially linked. The authors cite the study findings and characterize the problems revealed. The article is prepared within the framework of the Government Order “Information support of scientific research of scientists and specialists on the basis of the RNPLS&T Open Archive as the scientific knowledge aggregation system, (FNEG-2022-003)” for the years 2022–2024.

Relevance in processing search queries to bibliographic and fulltext databases in the modern models of scientific research support through open archives

RNPLS&T has been developing the model Single Open Information Archive (SOIA) to integrate all digital fulltext resources created and acquired by the Library. Beside its own content sources, the SOIA portal is to offer user services, among them use of other open repositories’ metadata (primarily that of Russian repositories) as the complementary source in processing of user search queries. Today, the functionality of extended metadata in information retrieval and data exchange has been being studied. This calls for investigating into the problem of relevance in processing search queries for both end users and for exchanging bibliographic and fulltext information between open archives. The purpose of this analysis is to specify the methods and technologies to increase the relevance. The findings of the analysis are cite; the revealed problems are characterized.

Developing Smart Web-Search using Regex

Due to the increasing storage data on the Web Applications it becomes very difficult to use only keywordbased searches to provide comprehensive search results, thus increasing the difficulty for web users to search information on the web. In this paper, we proposed using a combined method of keyword-based and Regular expressions (RegEx) searches to perform search using strings of targeted items for optimal results even as the volume of data around the world on the Internet continues to explode. The idea is to embed RegEx patterns as part of search engine’s algorithm in a web application project to provide strings related to the targeted items for more comprehensive coverage of search results. The user's search query is a string of characters guided by search boundaries selected from the entry point. The results returned from the search operation are different results within a category determined by the search boundaries. This is designed to be beneficial to a user who has an obscure idea about the information he/she wanted to search but knows the boundries within which to get the information. This technique can be applied to data processing tasks such as information extraction and search refinements.

Internet Space and Artificial Intelligence: Problems of Entrepreneurship and Law Enforcement

Introduction: the author investigates the problems of carrying out a special type of entrepreneurial activity – advertising goods and services by public-media individuals on the Internet, through their personal accounts in social networks. Formally, these individuals are not individual entrepreneurs they mention certain goods and services indirectly, in the process of communicating with other users of social networks. Such an advertising business is based on the analysis and accumulation of user search queries, because of which special computer algorithms are launched, and instantly give this user numerous answers and suggestions about goods and services. In the current period, such remote services in the information and communication network Internet are provided to users with the help of artificial intelligence. Methods: a number of problems of using artificial intelligence are highlighted, the features of the legal responsibility of the person who owns this computer-software resource, as a person who is an employer from the standpoint of labor law, are revealed. Results: it is proposed to legislate the special entrepreneurial status of “self-employed in the information and telecommunications network Internet”. A variant of a special tax regime for such entrepreneurial activity is proposed too. The conclusion is substantiated that public-media individuals who have continuous Internet communications with other persons in the number of at least 1 million persons on average per year should, by virtue of the law, be given a special entrepreneurial status, provided that they do not have a written refusal from advertising activities. Compliance with such a refusal and the actual non-implementation by a public media person of advertising activities in social networks is also controlled by artificial intelligence.

Combination of data mining and artificial intelligence algorithms for efficient web page recommendation

Due to the obvious unstable increase in information, the web is saturated with data, which makes the data search a complicated task. Existing web-based recommendation systems include shortcomings such as a lack of capability as well as scalability when dealing with online data, and blockages created by traffic while utilising the website during peak hours. Web recommendation systems help consumers find the right content and make the information search process easier. Web usage mining is regarded as the primary source for web recommendation, and it is used in conjunction with association rule mining and the C4.5 algorithm to recommend online pages to the user. The Google search engine has been widely enhanced the likelihood on the system's suggested structure. A web log is created when a user enters a search query into a search engine. This query would be compared to the web logs by the proposed system. The associate rule mining technique helps in matching the user's search query to the online log. The C4.5 algorithm is linked to a priority based on reviews, which obviously ranks the search based on priority for greater validation result.

Who to show the ad to? Behavioral targeting in Internet advertising

PurposeThe performance of behavioral targeting (BT) mainly relies on the effectiveness of user classification since advertisers always want to target their advertisements to the most relevant users. In this paper, the authors frame the BT as a user classification problem and describe a machine learning–based approach for solving it.Design/methodology/approachTo perform such a study, two major research questions are investigated: the first question is how to represent a user’s online behavior. A good representation strategy should be able to effectively classify users based on their online activities. The second question is how different representation strategies affect the targeting performance. The authors propose three user behavior representation methods and compare them empirically using the area under the receiver operating characteristic curve (AUC) as a performance measure.FindingsThe experimental results indicate that ad campaign effectiveness can be significantly improved by combining user search queries, clicked URLs and clicked ads as a user profile. In addition, the authors also explore the temporal aspect of user behavior history by investigating the effect of history length on targeting performance. The authors note that an improvement of approximately 6.5% in AUC is achieved when user history is extended from 1 day to 14 days, which is substantial in targeting performance.Originality/valueThis paper confirms the effectiveness of BT on user classification and provides a validation of BT for Internet advertising.

Development of Chatbots to Support Web Site Content Search Based on Thematic and Genre Characteristics

The paper considers an approach to creating intelligent assistants in the form of chatbots that support information search based on preliminary genre and thematic clustering of website content. The tasks of finding the necessary in-formation and providing information support to the user, organizing feedback to improve the quality of the search are being solved. A feature of the approach is the use of genre models developed for a given type of resource (educational, informational, etc.), on the basis of which genre structuring of the content of a particular site is carried out. The resulting genre structures allow you to more accurately determine the boundaries of thematic clusters related to the topic of the user's search query. To provide feedback to the user, a simple script has been developed that allows not only to clarify the request, but also to implicitly get information about what exactly did not suit the user in the resulting out-put. An experimental study was conducted on the Telegram platform, the results were compared with the Yandex search engine.

ОНТОЛОГИЧЕСКАЯ МОДЕЛЬ ОБРАЗОВАТЕЛЬНОГО ПОРТАЛА ВУЗА

The article discusses the main aspects of building the ontology of the educational portal of the university from design to development. Examples of working with Protégé 4.3 and Sparql queries are given. In addition, the author talks about the importance of working on an educational portal in terms of developing the semantic core and the relevance of the portal for search engines. The author proposes a methodology for using Semantic Web technologies to form the structure and content of the university's educational portal. Develop an ontology of the educational portal to provide the possibility of semantic analysis of user search queries in order to organize a rational structure and content of the educational portal of the university and ensure the possibility of effective promotion of the portal in the Internet environment. In the ontological model, the author considers in the form of classes a set of educational programs of the university, and their constituent educational courses, as well as user profiles. Relations between classes will further help, when implementing user information requests, to determine the degree of compliance of each educational program (field of study) with the needs and preferences of a particular user, and to implement automatic selection of university educational programs recommended for applicants. An ontological model of the educational portal has been developed. The ontological model allows you to optimally structure the content of the educational portal, which further provides the possibility of issuing recommendations to users regarding the choice of the direction of training (applicants) or educational resources (students or teachers) in accordance with their needs and preferences. The developed ontology is used both at the stage of developing the educational portal of the university and its semantic core, and at the stage of functioning of the educational resource, as a knowledge base in the system for issuing recommendations to users on choosing the direction of training.

DEVELOPMENT OF ARCHITECTURE OF MESSAGE QUEUE BASED INFORMATION SEARCH SYSTEMS FOR ENTERPRISE INFORMATION SYSTEMS

oday, information search has become not only an ordinary skill for users of information systems, but also an essential part of business. The amount of data that organizations own is growing day by day. Accordingly, it becomes difficult to find the necessary information in this data, especially if it is allocated in different storages. To facilitate the search in enterprise information systems, information search systems with a single graphical interface and ability to search in different data sources are used. There are ready-made software packages on the market, though some companies opt out to develop their own search engine. In the latter case, however, it is critical to be scrupulous designing the system architecture to comply with all the requirements that are imposed on this kind of software today. Information search systems for enterprise information systems. The purpose of the study was to describe the main architectural approaches to developing information search systems and identify their strong and weak points; to form basic ideas for the development of the architecture of information search systems based on message queues and to describe the main components of such systems; to elaborate on the key aspects of the practical implementation of the data warehouse of user search queries and the results of their processing. The paper considers the results of studies on the typical problems which employees face during information search in enterprise applications. The authors evaluate the existing architectural approaches to information search systems, analyze and compare two of the most popular message brokers. The article substantiates the relevance of the problem of finding information in enterprise information systems. The authors provide a description of the main approaches to the architecture of information search systems, go into their advantages and disadvantages, and provide architectural diagrams of the components. The microservices that make up a message queue-based system are described. Kafka is chosen and substantiated as the most suitable message broker. The authors also give a graphical scheme of handling errors that arise during search services operation.

Application of convolution neural network in web query session mining for personalised web search

In this paper, a deep learning convolution neural network (CNN) is applied in web query session mining for effective personalised web search. The CNN extracts high-level continuous clicked document/query concept vector for semantic clustering of documents. The CNN model is trained to generate document/query concept vector based on clickthrough web query session data. Training of CNN is done using backpropagation based on stochastic gradient descent maximising the likelihood of relevant document given a user search query. During web search, search query concept vector is generated and compared with semantic clusters means to select the most similar cluster for web document recommendations. The experimental results were analysed based on average precision of search results and loss function computed during training of CNN. The improvement in precision of search results as well as decrease in loss value proves CNN to be effective in capturing semantics of web user query sessions for effective information retrieval.

Covid-19 impact on business sector activity in the EUcountries: digital issues

This article is devoted to the study of the impact of the COVID-19 pandemic on the functioning of the business sector of European countries through bibliometric analysis. The purpose of this paper is to analyze the scientific achievements on this topic in terms of identifying key categories and phenomena that characterize the impact of COVID-19 on the activities of business entities. Methodological support for this paper includes trend and bibliometric analysis (based on VOSViewer v.1.6.10 toolkit). The results of the trend analysis showed recent stable gradual growth in the number of user search queries on business issues caused more by the COVID-19 pandemic that has become an inhibitor of economic growth and sustainable development. The object of the paper is 2406 publications indexed in the Scopus database and 4666 publications indexed in the Web of Science database on the effects of pandemics on the business sector. The time horizon of the study was in 1980-2021. According to the results of the analysis of papers indexed in the Scopus database the decreasing number of papers during 2014-2015 (from 99225 to 28836) were identified. The article identifies the top 15 Scientific Journals indexed by the Scopus and Web of Science databases in which the issue of the effects of COVID-19 on the business sector were considered most often. It is concluded that the majority of publications were published in journals that were indexed in both databases – Scopus and Web of Science. According to the results of the analysis of metadata of publications devoted to the effects of COVID-19 on the business sector, the 9 clusters by the Scopus database and 8 clusters by the WoS database were identified. The results of the bibliometric analysis devoted to the effects of COVID-19 on the business sector allowed defining 10587 keywords, the frequency of use of which exceeds 5. According to the Scopus database the most popular keywords within this problem are: humans, female, organization and management, commerce, risk assessment, economic aspect and others. At the same time, the most popular keywords in the Web of Science database are: pandemic, impact, business, performance, crisis, management, entrepreneurship, innovation.

Метод разрешения лексической многозначности поискового запроса на основе онтологий

One of the factors influencing the relevance of search output is the multivalued search query, expressed by lexical means of a natural language. The multivalued lexical unit manifests itself at the stage of a search query. The method of removing the multivalence of lexical units in a search query based on ontologies is proposed. It is grounded that ontologies allow transferring semantic component of data related to a subject area accurately enough. The proposed method for lexical multivariance resolution can be described as follows. A user search query is received at the search engine input. The search engine contacts the ontology library to find the query. If the lexical unit from the search query is multivalued, the search engine will offer the user a list of subject areas in which the lexical unit from the search query was found. Oft the user searches in advance for the result from a particular subject area. When the subject area is defined, the search engine determines the nearest elements in the structure of ontology, and when ranking the search output will be guided by their presence or absence. The use of ontologies also allows adding synonyms and acronyms meaning the same to the search query. The proposed approach will allow solving lexical multiplicity and significantly relieving the search output, leaving only the subject area of interest to the user.

Deep Learning-based Extraction of Algorithmic Metadata in Full-Text Scholarly Documents

The advancements of search engines for traditional text documents have enabled the effective retrieval of massive textual information in a resource-efficient manner. However, such conventional search methodologies often suffer from poor retrieval accuracy especially when documents exhibit unique properties that behoove specialized and deeper semantic extraction. Recently, AlgorithmSeer, a search engine for algorithms has been proposed, that extracts pseudo-codes and shallow textual metadata from scientific publications and treats them as traditional documents so that the conventional search engine methodology could be applied. However, such a system fails to facilitate user search queries that seek to identify algorithm-specific information, such as the datasets on which algorithms operate, the performance of algorithms, and runtime complexity, etc. In this paper, a set of enhancements to the previously proposed algorithm search engine are presented. Specifically, we propose a set of methods to automatically identify and extract algorithmic pseudo-codes and the sentences that convey related algorithmic metadata using a set of machine-learning techniques. In an experiment with over 93,000 text lines, we introduce 60 novel features, comprising content-based, font style based and structure-based feature groups, to extract algorithmic pseudo-codes. Our proposed pseudo-code extraction method achieves 93.32% F1-score, outperforming the state-of-the-art techniques by 28%. Additionally, we propose a method to extract algorithmic-related sentences using deep neural networks and achieve an accuracy of 78.5%, outperforming a Rule-based model and a support vector machine model by 28% and 16%, respectively.

Deep Learning for Adverse Event Detection from Web Search

Adverse event detection is critical for many real-world applications including timely identification of product defects, disasters, and major socio-political incidents. In the health context, adverse drug events account for countless hospitalizations and deaths annually. Since users often begin their information seeking and reporting with online searches, examination of search query logs has emerged as an important detection channel. However, search context - including query intent and heterogeneity in user behaviors - is extremely important for extracting information from search queries, and yet the challenge of measuring and analyzing these aspects has precluded their use in prior studies. We propose DeepSAVE, a novel deep learning framework for detecting adverse events based on user search query logs. DeepSAVE uses an enriched variational autoencoder encompassing a novel query embedding and user modeling module that work in concert to address the context challenge associated with search-based detection of adverse events. Evaluation results on three large real-world event datasets show that DeepSAVE outperforms existing detection methods as well as comparison deep learning auto encoders. Ablation analysis reveals that each component of DeepSAVE significantly contributes to its overall performance. Collectively, the results demonstrate the viability of the proposed architecture for detecting adverse events from search query logs.

Scavenge: an intelligent multi-agent based voice-enabled virtual assistant for LMS

ABSTRACT The existing Learning Management Systems (LMSs) are profoundly effective in empowering the organization of e-learning, however, lacking in usability and learnability. The complex navigation and an immature search system are catalysing the issues that needs vigorous improvement. This paper aims to enhance the usability of LMSs by introducing an intelligent multi-agent based voice-enabled virtual assistant, named Scavenge. The Scavenge can work with LMS to speed-up user tasks through natural voice-command (or text). It can perform many internal and external actions without a mouse or keyboard clicks, and capable to provide the results of user search queries. A prototype system was developed with Moodle LMS and conducted a usability test based on ISO/IEC 9126-4 usability metrics that are effectiveness, efficiency, and satisfaction. A group of University students were selected, who were involved in the usability testing of the proposed system. The results have shown that the proposed system has a positive impact on students’ performance and can enhance the usability of LMS. The approach and techniques used in Scavenge are novel and innovative that will be a valuable contribution to the overall field of knowledge.

THE METHOD OF DYNAMIC DESIGN OF A SEARCH ENGINE BASED ON AUTOMATED ANALYSIS OF USER REQUESTS

The article describes the method of dynamically designing a search engine based on the analysis of user search queries and automated user's document generation. The advanced method of dynamic search with the account of individual features of users is offered, which allows to increase the cost of search. The service for designing own search engine is created. It replaces the algorithm of ranking on the algorithm for sorting search engines by category using the pseudo relevance feedback method. The information is filled in with a system of successive objects, which is a list. Objects contain key information, these keys allow to set up work with information and increase the relevance of the search. The service contains graphical tools for updating, storing and deleting information in the search engine. An analysis of the configuration of the search service is performed to increase the end-user search cost. There is a conclusion of the results, which indicates the shortcomings of the search engine developer of this system and generated documentation on its use based on the settings for the end user. The sorting system analyzes the end-user request and provides the information it finds, sorted by relevancy. The developed method provides acceleration of the algorithm of the search engine and the quality of the information found for the user.