Information Retrieval Tools Research Articles

Enhancement of the Performance of Large Language Models in Diabetes Education through Retrieval-Augmented Generation: Comparative Study.

Large language models (LLMs) demonstrated advanced performance in processing clinical information. However, commercially available LLMs lack specialized medical knowledge and remain susceptible to generating inaccurate information. Given the need for self-management in diabetes, patients commonly seek information online. We introduce the Retrieval-augmented Information System for Enhancement (RISE) framework and evaluate its performance in enhancing LLMs to provide accurate responses to diabetes-related inquiries. This study aimed to evaluate the potential of the RISE framework, an information retrieval and augmentation tool, to improve the LLM's performance to accurately and safely respond to diabetes-related inquiries. The RISE, an innovative retrieval augmentation framework, comprises 4 steps: rewriting query, information retrieval, summarization, and execution. Using a set of 43 common diabetes-related questions, we evaluated 3 base LLMs (GPT-4, Anthropic Claude 2, Google Bard) and their RISE-enhanced versions respectively. Assessments were conducted by clinicians for accuracy and comprehensiveness and by patients for understandability. The integration of RISE significantly improved the accuracy and comprehensiveness of responses from all 3 base LLMs. On average, the percentage of accurate responses increased by 12% (15/129) with RISE. Specifically, the rates of accurate responses increased by 7% (3/43) for GPT-4, 19% (8/43) for Claude 2, and 9% (4/43) for Google Bard. The framework also enhanced response comprehensiveness, with mean scores improving by 0.44 (SD 0.10). Understandability was also enhanced by 0.19 (SD 0.13) on average. Data collection was conducted from September 30, 2023 to February 5, 2024. The RISE significantly improves LLMs' performance in responding to diabetes-related inquiries, enhancing accuracy, comprehensiveness, and understandability. These improvements have crucial implications for RISE's future role in patient education and chronic illness self-management, which contributes to relieving medical resource pressures and raising public awareness of medical knowledge.

How user language affects conflict fatality estimates in ChatGPT

OpenAI’s ChatGPT language model has gained popularity as a powerful tool for problem-solving and information retrieval. However, concerns arise about the reproduction of biases present in the language-specific training data. In this study, we address this issue in the context of the Israeli–Palestinian and Turkish–Kurdish conflicts. Using GPT-3.5, we employed an automated query procedure to inquire about casualties in specific airstrikes, in both Hebrew and Arabic for the former conflict and Turkish and Kurdish for the latter. Our analysis reveals that GPT-3.5 provides 34 ± 11% lower fatality estimates when queried in the language of the attacker than in the language of the targeted group. Evasive answers denying the existence of such attacks further increase the discrepancy. A simplified analysis on the current GPT-4 model shows the same trends. To explain the origin of the bias, we conducted a systematic media content analysis of Arabic news sources. The media analysis suggests that the large-language model fails to link specific attacks to the corresponding fatality numbers reported in the Arabic news. Due to its reliance on co-occurring words, the large-language model may provide death tolls from different attacks with greater news impact or cumulative death counts that are prevalent in the training data. Given that large-language models may shape information dissemination in the future, the language bias identified in our study has the potential to amplify existing biases along linguistic dyads and contribute to information bubbles.

Intelligible graph contrastive learning with attention-aware for recommendation

Recommender systems are an important tool for information retrieval, which can aid in the solution of the issue of information overload. Recently, contrastive learning has shown remarkable performance in recommendation by data augmentation processes to address highly sparse data. Our paper proposes an Intelligible Graph Contrastive Learning with attention-aware (IntGCL) for recommendation. Particularly, our IntGCL first introduces a novel attention-aware matrix into graph convolutional networks (GCN) to identify the importance between users and items, which is constructed to preserve the importance between users and items by a random walk with a restart strategy and can enhance the intelligibility of our model. Then, the attention-aware matrix is further utilised to guide the generation of a graph-generative model with attention-aware and a graph-denoising model for automatically generating two trainable contrastive views for data augmentation, which can de-noise and further enhance the intelligibility. Comprehensive experiments on four real-world datasets indicate the superiority of our IntGCL approach over multiple state-of-the-art methods. Our datasets and source code are available at https://github.com/restarthxr/InpGCL.

Development of an Evaluation Instrument on Artificial Intelligence Search Tools for Evidence Synthesis

Canada’s Drug Agency has developed an instrument to monitor and evaluate artificial intelligence tools for information retrieval so that, as these tools evolve, we can leverage them appropriately. We are sharing our instrument to help other evidence synthesis producers evaluate and make use of artificial intelligence tools for information retrieval.

Optimizing the Utilization of Online Public Access Catalog as a Means of Information Retrieval in Libraries

This study aims to explore the optimization of the Online Public Access Catalogue (OPAC) as an information retrieval tool in the Library of SMA Negeri 3 Medan, focusing on identifying the challenges and barriers to its effective use. A qualitative descriptive approach was employed, utilizing interviews, observations, and documentation as data collection methods. Interviews were conducted with a librarian and three students, while observations focused on the practical issues related to OPAC usage. The findings reveal that the use of OPAC in the library is not optimal, with challenges including system integration difficulties, insufficient librarian training, and limited user familiarity. Efforts to enhance OPAC usage involve promoting OPAC awareness, increasing computer access points, and ongoing system maintenance. However, the effectiveness of these measures is hindered by technical and educational constraints, highlighting the need for targeted interventions to fully leverage OPAC's potential in improving library services.

Marine information-seeking behaviours and AI chatbot impact on information discovery

Purpose This research investigates students’ information-seeking behaviours at the Indian Maritime University (IMU) and assesses the impact of AI chatbots on their marine science knowledge and awareness. The study aims to provide insights into the role of AI-driven solutions in enhancing knowledge sharing and the challenges faced in using AI tools for marine information retrieval. Design/methodology/approach The study used a stratified random sampling method, encompassing 152 respondents from IMU’s B.Sc. in Nautical Science and B. Tech in Marine Engineering programs. Data collection involved a structured electronic survey questionnaire. The analysis encompassed descriptive statistics using SPSS. Findings Information needs were met through diverse channels, with 57.9% of respondents using AI-driven chatbots for marine information retrieval. AI significantly recommended research papers (61.8%). The chatbot positively impacted marine science awareness and knowledge, with a mean satisfaction rating of approximately 3.3. Challenges included insufficient access to AI tools, data privacy concerns and accuracy issues. Originality/value This study contributes original insights into the information-seeking behaviours of marine students at IMU and the impact of AI chatbots on their knowledge and awareness. It highlights the multifaceted nature of marine information retrieval, the effectiveness of AI-driven solutions in enhancing knowledge sharing and the challenges that need to be addressed for the broader adoption of AI tools in this context.

ChatGPT: A Conceptual Review of Applications and Utility in the Field of Medicine.

Artificial Intelligence, specifically advanced language models such as ChatGPT, have the potential to revolutionize various aspects of healthcare, medical education, and research. In this narrative review, we evaluate the myriad applications of ChatGPT in diverse healthcare domains. We discuss its potential role in clinical decision-making, exploring how it can assist physicians by providing rapid, data-driven insights for diagnosis and treatment. We review the benefits of ChatGPT in personalized patient care, particularly in geriatric care, medication management, weight loss and nutrition, and physical activity guidance. We further delve into its potential to enhance medical research, through the analysis of large datasets, and the development of novel methodologies. In the realm of medical education, we investigate the utility of ChatGPT as an information retrieval tool and personalized learning resource for medical students and professionals. There are numerous promising applications of ChatGPT that will likely induce paradigm shifts in healthcare practice, education, and research. The use of ChatGPT may come with several benefits in areas such as clinical decision making, geriatric care, medication management, weight loss and nutrition, physical fitness, scientific research, and medical education. Nevertheless, it is important to note that issues surrounding ethics, data privacy, transparency, inaccuracy, and inadequacy persist. Prior to widespread use in medicine, it is imperative to objectively evaluate the impact of ChatGPT in a real-world setting using a risk-based approach.

Yury Nikolaevich Stolyarov: Remains in the memory…

The article is dedicated to the memory of Yury N. Stolyarov, an outstanding Russian library scholar. Through personal memories, the image is drawn of an enthusiastic scientist, a man of extensive knowledge, true culture and modesty. The impact of Stolyarov’s scientific ideas of Yury N. Stolyarov is demonstrated through the analysis of citations of his works using the RSCI information retrieval tools.

A NOVEL APPROACH TO SECURE WEB SEARCH: PROXY-QUERY BASED QUERY OBFUSCATION

Web search engines are used by people to access content on the internet. To improve the quality of the information received for individualized web searches, search engines keep query logs. User information, both sensitive and non-sensitive, is included in the query log. The query log can expose a great deal of personal information about a person and raise privacy issues if used against them. To achieve privacy-preserving online search, numerous private web search (PWS) systems have been proposed in recent years. While every PWS system claims to have special features that enable web search privacy (WSP), no study clarifies which properties related to private web searches should be taken into account when developing and implementing a PWS scheme. This article aims to accomplish two things. We introduce a new PWS strategy that employs a proxy-query-based query obfuscation method in the first section of the paper. In PWS research, proxy-query-based query obfuscation is a novel research area. Through proxy queries, it offers an IR tool for information retrieval from web search engines. The suggested system has the obvious benefit of preventing users from actually asking search engines questions in order to retrieve information. The second goal of the article is to identify PWS features and examine contemporary PWS systems in light of these attributes. We examined contemporary and suggested PWS systems based on PWS attributes. The investigation showed that only the suggested PWS design satisfies every requirement. Since existing PWS systems do not meet all PWS requirements, it has been found that they are susceptible to WSP attacks. Key Words: Private web search, Web search privacy, Proxy-query, Query Obfuscation, Information Retrieval, Cryptographic Authentication

A Textbook for Researchers. Review of the Textbook “Information Resources and Tools in the Researcher’s Work” by V. N. Gureyev and N. A. Mazov

The author reviews a textbook written by Vadim N.Gureyev and Nikolay A.Mazov (Trofimuk Institute of Petroleum Geology and Geophysics of the SB RAS). The review notes the scale of content coverage, good organization of the material, high relevance and novelty of the information presented in the textbook. From the perspective of a researcher and university lecturer, the reviewer examines certain aspects of five chapters of the textbook, which provide characteristics of modern publishers of academic literature, databases of scientific publications and journals, identifiers for research works and authors, classification systems of scientific knowledge and bibliometric indicators. The review emphasizes the uniqueness of the publication as a kind of professional reference book for researchers, from young authors to established scholars. The methodological part of the textbook and its auxiliary apparatus are characterized positively. The presentation of the material shows a combination of logic and conciseness, which illustrates the principle of necessity and sufficiency when selecting content to achieve the stated purpose of the educational publication and provides readers with quick access to necessary information. The reviewer gives reasons of the wide readership of the publication, including its undoubted value for library workers and expresses a wish to present materials that deal with researcher’s information retrieval tools in the form of a separate structural part of the textbook. The work is assessed as a relevant authors’ contribution to the series of, so far, few educational publications in the field of research communications. The review is accompanied by a bibliographic list of the most significant works co-authored by V.N.Gureyev and N.A.Mazov.

Enriching Portuguese Medieval Texts with Named Entity Recognition

Historical data poses unique challenges to natural language processing (NLP) and information retrieval (IR) tools, including digitization errors, lack of annotated data, and diachronic-specific issues. However, the increasing recognition of the value in historical documents has promoted efforts to semantically enrich and optimize their analysis. This article contributes to this endeavour by enriching the Corpus de Textos Antigos through NLP tools and techniques to enhance its usability and support research. The corpus undergoes linguistic annotation, including part-of-speech tagging, lemma annotation and named entity recognition (NER). Subsequently, the article delves into the tasks of entity disambiguation and entity linking, which involve identifying and disambiguating named entities by referring to a knowledge base (KB). Addressing the challenges posed by factors such as text state, epoch and the chosen KB, the article presents insights into related work, annotation results and the linguistic interest of a medieval annotated corpus for named entities. It concludes by discussing the challenges and providing avenues for future research in this domain.

An Update on the Use of Artificial Intelligence in Cardiovascular Medicine

Artificial intelligence, specifically advanced language models such as ChatGPT, have the potential to revolutionize various aspects of healthcare, medical education, and research. In this review, we evaluate the myriad applications of artificial intelligence in diverse healthcare domains. We discuss its potential role in clinical decision-making, exploring how it can assist physicians by providing rapid, data-driven insights for diagnosis and treatment. We review the benefits of artificial intelligence such as ChatGPT in personalized patient care, particularly in geriatric care, medication management, weight loss and nutrition, and physical activity guidance. We further delve into its potential to enhance medical research, through the analysis of large datasets, and the development of novel methodologies. In the realm of medical education, we investigate the utility of artificial intelligence as an information retrieval tool and personalized learning resource for medical students and professionals.

Comparing ChatGPT and Google Bard: Assessing AI-Powered Information Retrieval in Nursing

Introduction In healthcare, rapid access to accurate information is essential, especially for nurses who make critical decisions. Artificial intelligence (AI) offers promise in this context, with ChatGPT and Google Bard being notable AI-driven information retrieval tools. Methods This study evaluated ChatGPT and Google Bard's performance by assessing their responses to 50 diverse medical knowledge questions, covering infection control, vital signs, CPR, and more, and comparing their response to the correct answers. Results ChatGPT achieved a 64% accuracy rate, while Google Bard achieved 56%. Both models agreed on key medical concepts, but disagreements emerged in some areas, highlighting disparities in their responses. Nurses' expertise in patient-centered care, clinical judgment, and communication complements AI. AI aids in providing evidence-based information but cannot replace nurses' human touch and critical thinking. Integrating AI into nursing education enhances learning and prepares professionals for evolving healthcare landscapes. Conclusion ChatGPT and Google Bard have strengths and weaknesses, making them valuable aids but not substitutes for nurses. Ethical considerations are vital as AI continues to shape healthcare. Nurses must ensure ethical AI use while upholding their commitment to compassionate care.

Revisiting Probabilistic Latent Semantic Analysis: Extensions, Challenges and Insights

This manuscript provides a comprehensive exploration of Probabilistic latent semantic analysis (PLSA), highlighting its strengths, drawbacks, and challenges. The PLSA, originally a tool for information retrieval, provides a probabilistic sense for a table of co-occurrences as a mixture of multinomial distributions spanned over a latent class variable and adjusted with the expectation–maximization algorithm. The distributional assumptions and the iterative nature lead to a rigid model, dividing enthusiasts and detractors. Those drawbacks have led to several reformulations: the extension of the method to normal data distributions and a non-parametric formulation obtained with the help of Non-negative matrix factorization (NMF) techniques. Furthermore, the combination of theoretical studies and programming techniques alleviates the computational problem, thus making the potential of the method explicit: its relation with the Singular value decomposition (SVD), which means that PLSA can be used to satisfactorily support other techniques, such as the construction of Fisher kernels, the probabilistic interpretation of Principal component analysis (PCA), Transfer learning (TL), and the training of neural networks, among others. We also present open questions as a practical and theoretical research window.

Is it the new Google: Impact of ChatGPT on Students' Information Search Habits

The traditional subject of information search and retrieval (IR) paradigm shifted to an entirely new era since artificial intelligence (AI) techniques were introduced into the field. Browser-based IR solutions powered by AI for personalised recommendations-based information retrieval, such as the Google search engine, were one of the early examples. The IR field has advanced to its next level with the newest conversational applications based on large language model (LLM) techniques. It is becoming clear that Generative Pretrained Transformer (GPT) applications such as ChatGPT will significantly impact information retrieval behaviour in the education sector. Though this application has become widespread in acclaim, no previous study has shown its impact on information seeking and retrieval. However, based on the observation of the fast penetration of this technology and the growth of public interest, a pre-assumption was built that it is essential to investigate if students may also be showing a similar interest in this new tool. Hence, this study is set up to systematically and empirically explore how ChatGPT influences the IR behaviour of students in HEIs. A survey approach is utilised to collect the perceived IR behaviour through a questionnaire administered to 60 students in HEIs. The findings reveal that the tool is already widely known among HEI students. They also perceived the use of the tool in the context of information retrieval and proclaimed its usefulness, acknowledging its efficiency (reduced time) in finding information. Furthermore, the technology has considerably affected the typical use of other conventional information retrieval and search engine tools. On the contrary, 10% of the respondents are less likely to use ChatGPT during information seeking for various reasons, from credibility and relevance to technology infrastructure issues such as connectivity. Although a deeper analysis is required to establish a general conclusion on how and in which ways GPT-based models will override contemporary IR practices, the study outcome provides evidence for a possible behavioural change among HEI students in their IR habits in the future.

Development of OpenAI API Based Chatbot to Improve User Interaction on the JBMS Website

This study presents an innovative chatbot, powered by OpenAI API, designed to enhance the user experience on the Journal of Business, Management, and Social Studies (JBMS) website. Chatbots have gained prominence for improving online interactions and information retrieval. The chatbot's development followed a structured prototype methodology, including Requirement Gathering, Prototype Building, Requirement Refinement, Customer Evaluation, and Design and Implementation. User Acceptance Testing (UAT) scored an average of 4.14, signifying high user satisfaction. UAT results showed positive user experiences and satisfaction with the chatbot. Integration of OpenAI API improved information extraction from journal articles and personalized article recommendations. Stakeholder feedback from JBMS's CEO, students, and UMN lecturers affirmed high satisfaction levels. Future research will refine the chatbot's features to align better with user needs, solidifying its role as an innovative tool for information retrieval within JBMS, and enhancing user service.

Document Difficulty Aspects for Medical Practitioners: Enhancing Information Retrieval in Personalized Search Engines

Timely and relevant information enables clinicians to make informed decisions about patient care outcomes. However, discovering related and understandable information from the vast medical literature is challenging. To address this problem, we aim to enable the development of search engines that meet the needs of medical practitioners by incorporating text difficulty features. We collected a dataset of 209 scientific research abstracts from different medical fields, available in both English and German. To determine the difficulty aspects of readability and technical level of each abstract, 216 medical experts annotated the dataset. We used a pre-trained BERT model, fine-tuned to our dataset, to develop a regression model predicting those difficulty features of abstracts. To highlight the strength of this approach, the model was compared to readability formulas currently in use. Analysis of the dataset revealed that German abstracts are more technically complex and less readable than their English counterparts. Our baseline model showed greater efficacy than current readability formulas in predicting domain-specific readability aspects. Conclusion: Incorporating these text difficulty aspects into the search engine will provide healthcare professionals with reliable and efficient information retrieval tools. Additionally, the dataset can serve as a starting point for future research.

The false positives and false negatives of generative AI detection tools in education and academic research: The case of ChatGPT

Generative Pre-trained Transformers like ChatGPT are examples of AI systems which produce human-like responses in different forms such as text or images that have demonstrated excellent performance in producing logical and contextually relevant answers. However, the false positive/negative detection of generative AI has been noted as a challenge. In this article, statistical experiments are conducted to test the chances of false positive and false negative detection of AI-generated text. It was found that the detected likelihoods of generative AI in articles’ abstracts is much lower than that found in paragraphs taken from the literature section of the selected articles. This means that literature parts have higher likelihoods to falsely demonstrate AI-generated text. On the other hand, when genuine texts are compared with AI-generated texts, it is observed that there is a noticeable margin of overlap between their distributions and therefore type I and type II errors fall within the realm of possibility. We show that despite these challenges, generative AI like ChatGPT continues to be a promising tool for communication and information retrieval. However, it is vital to address the concerns regarding false detection of AI generated text and ensure that these models are used in ethical and responsible conduct.

A Novel Architecture for Search Engine using Domain Based Web Log Data

Search engines, an information retrieval tool are the main source of information for users’ information need now a day. For every query, the search engine explores its repository and/or indexer to find the relevant documents/URLs for that query. Page ranking algorithms rank the Uniform Resource Locator in abstract section (URLs) according to its relevancy with respect to users’ query. It is analyzed that many of the queries fired by users on search engines are duplicate. There is a scope to improve the performance of search engine to reduce its efforts for duplicate queries. In this paper a proxy server is created that keep store the search results of user queries in web log. The proposed proxy server uses this web log to find results faster for duplicate queries fired next time. The proposed scheme has been tested and found prominent. The proposed architecture tested for ten duplicate user queries. it return all relevant web pages for duplicate user query (if query is found in web log at proxy server) from a particular domain instead of entire database. It reduces the perceived latency for duplicate query and also improves the value of precession and accuracy up to 81.8% and 99% respectively for all duplicate user queries.

Attempts of Lithuanian State Archive Institutions to Search for Archived Heritage Exported from Lithuania in the Past or Related to Lithuania

As archival institutions are operating under the conditions of globalization, digital culture, and technological changes, displaced archives are evaluated from various aspects (theoretical, sociopolitical, or technological). Ensuring the accessibility of displaced archives remains the fundamental goal of archives, which is inseparable from the strategies of document heritage accumulation (acquisition) in archives, the application of archival principles or document concepts, knowledge of the history of a country or a specific region, and knowledge of the legal system. The research and good practice of displaced archives is also of importance for the state archives of Lithuania. Professor Zigmantas Kiaupa discussed the efforts by archives in an attempt to recover documents illegally exported from Lithuania. However, searches for the archival heritage by the Lithuanian state archives after 1990 have not become the object of scientific publications.
 The article gives a review of the actions of the state archives system since 1990 which was aimed at identifying the documentary heritage related to Lithuania but preserved abroad. The focus of attention is on the creation of legal regulation, accumulation of documents, and information about the identified documents related to Lithuania and the further activities of state archives. Archival sources show that, since 1990, the identification of documents related to Lithuania and preserved abroad along with the activity of their storage in Lithuania is a continuous and consistent process, although the scope of this activity is not large, and only a few archives have been participating in its implementation. The review of the activity of the Office of the Chief Archivist of Lithuania and the state archives proves that international agreements or agreements of cooperation between two countries contribute to the establishment of close professional relationships, but it is not a prerequisite for the document search. It is more important to provide methodological assistance to those who have preserved the documents related to Lithuania (especially to Lithuanians living abroad) as well as to coordinate the activities related to document management, their description, digitization, and publication, as these activities require different competencies.
 The article concludes that the legislative regulation of Lithuania created legal opportunities for the state archives to make independent decisions regarding the strategy of collecting documents related to Lithuania and to be more actively involved in the activities of digital cultural heritage actualization. The state archives of Lithuania do not associate the accumulation of documentary heritage related to Lithuania only with the physical form of documents. The article argues that the accumulation of digital cultural objects and the dissemination of descriptive information in archives using several information retrieval tools further complicates the accessibility of information. This is why the accumulation of information and its provision to the user, based on the one-stop-shop principle, should be regarded as a priority.