Information Retrieval Research Articles

Citywalk in China: analysis of regional and route characteristics

ABSTRACT The West introduced Citywalk to China; since then, the concept has undergone a significant transformation from mere walking or hiking activities, impacting people’s choices in transportation and urban spatial experiences. However, the defining characteristics of Citywalk remain unclear. To address this gap, this study considers representative cities in China as examples and employs a comprehensive approach including website information retrieval, SPSS software, and word frequency analysis to collect and analyze data on 611 Citywalk routes in 48 cities. The study objective is to examine the regional characteristics of Citywalk routes and elucidate the factors that shape Citywalk characteristics. Descriptive statistics are used to describe the regional characteristics of Citywalk routes, and three indicators – urban attributes, route features, and node types – are identified. Subsequently, correlation analysis is applied within and between groups. The results indicate a significant correlation among urban attributes, route features, and certain node types with high reliability. This study provides bottom-up data support for the design of linear spatial experiences in Chinese cities and the improvement of tourist route planning, thus offering valuable references for future endeavors in this field.

Decoding compositional complexity: Identifying composers using a model fusion-based approach with nonlinear signal processing and chaotic dynamics

Music, a universal medium that effortlessly transcends the confines of language and culture, serves as a vessel for the distinctive expression of a composer's ingenuity, particularly palpable through the elaborate symphony of melodies, harmonies, and rhythms. This phenomenon is acutely observable in the realm of Turkish Classical Music, where the identification of individual composers poses a formidable challenge due to a confluence of diverse stylistic expressions and sophisticated techniques. Shaped by centuries of cultural interchanges, this genre is celebrated for its convoluted rhythmic frameworks and deep melodic modes, often exhibiting fractal characteristics that compound the complexity of composer classification based on mere audio signals. In response to these complexities, this study introduces an advanced analytical paradigm that amalgamates Multi-resolution analysis, spectral entropy assessments, and a spectrum of multidimensional chaotic and statistical descriptors. By invoking chaos theory, the research delineates distinct patterns and features inherent to musical compositions, subsequently deploying these discoveries for composer categorization. Employing a model fusion-based strategy, the approach utilizes esteemed base estimators for section-level probabilistic determinations, subsequently amalgamated at the song level through a Long Short-Term Memory (LSTM) neural network model to classify a corpus of 380 compositions from 15 distinct composers. The results of this study not only highlight the efficacy of chaos-based approaches in Musical Information Retrieval but also provide a nuanced understanding of the unique characteristics of Turkish Classical Music, thus advancing the boundaries of how musicological data is scrutinized and conceptualized within scholarly discourse.

Cross media knowledge information retrieval model based on D-S evidence theory

Cross media knowledge information retrieval provides strong support for information processing and utilization in the information society, but there are problems such as heterogeneity in cross media knowledge information. Therefore, a cross media knowledge information retrieval model using D-S evidence theory is proposed, which involves using approximate calculation methods to improve this theory for information fusion, reducing computational complexity, and using deep networks for fine-grained information retrieval to improve retrieval accuracy. The results showed that the improved theory enhanced computational efficiency by about 27.23 %. The memory usage was <60 %, and the average accuracy of information fusion reached 93.14 %. It also exhibited high recall and low false alarm rates. The cross media knowledge information retrieval model proposed in the study achieved accuracy of 92.64 %, 96.49 %, and 97.46 % on the three datasets used in the experiment, respectively. The study provides an effective, computationally efficient, and highly accurate model for cross media knowledge information retrieval, which is expected to promote research and application in this field. The combination of improved D-S evidence theory and deep networks provides a powerful approach to solving the problem of cross media heterogeneous information retrieval, which has a positive promoting effect on the processing and utilization of information in the information society.

Can AI Make a Case? AI Vs. Lawyer in The Dutch Legal Context

The integration of AI, specifically GPT-4, into the legal field is a subject of both potential promise and intricate challenges. This thesis delves into the transformational possibilities of AI within the Dutch legal context, examining not only the quality and persuasiveness of AI-generated legal argumentation but also its competence in information retrieval, as measured by models’ ability to spot relevant legal issues. An experiment was conducted with 25 legal professionals, using a real-world Dutch case with the purpose to assess GPT-4’s capabilities against that of a human lawyer. To enable GPT-4 to handle case documents, the author first performed so-called co-reference resolution to remove ambiguities. Given the token limitations of GPT-4, a so-called prompt reducer technique was used to compress the text, retaining essential information. The above methods produced a coherent and full case summary within GPT-4’s token constraints. This case summary, together with original lawyer’s letter (denoted as Text A) was fed to ChatGPT-4 to obtain its AI-written alternative (Text B). The study subjects were presented with a case summary as well as both texts and asked for their preferences. The outcome of the experiment is as follow: 80% of participants chose the AI’s composed legal document, demonstrating a strong preference for both its linguistic competencies as well its ability to spot relevant legal issues. This preference for GPT-4 writing is very consistent among genders, age groups and professions surveyed. Contextualising these findings within the broader implications for legal practice, the thesis explores potential benefits including increased access to justice and transformation of certain legal procedures. Insights and recommendations are offered for legal professionals, considering the technological evolution and ethical considerations inherent in AI integration. Acknowledging the need for further exploration, the study recognises its own limitations and encourages replication to solidify the understanding of AI’s transformative role in the legal realm. GPT-4, AI, AI vs Lawyer, Legal Writing, Language Technology, LLM, Dutch Legal Context

[Translated article] The role of artificial intelligence in scientific publishing: perspectives from hospital pharmacy

The article examines the impact of artificial intelligence on scientific writing, with a particular focus on its application in hospital pharmacy. It analyses artificial intelligence tools that enhance information retrieval, literature analysis, writing quality, and manuscript drafting.Chatbots like Consensus, along with platforms such as Scite and SciSpace, enable precise searches in scientific databases, providing evidence-based responses and references. SciSpace facilitates the generation of comparative tables and the formulation of queries regarding studies, while ResearchRabbit maps the scientific literature to identify trends. Tools like DeepL and ProWritingAid improve writing quality by correcting grammatical, stylistic, and plagiarism errors. A.R.I.A. enhances reference management, and Jenny AI assists in overcoming writer's block. Python libraries such as langchain enable advanced semantic searches and the creation of agents.Despite their benefits, artificial intelligence raises ethical concerns including biases, misinformation, and plagiarism. The importance of responsible use and critical review by experts is emphasised. In hospital pharmacy, artificial intelligence can enhance efficiency and precision in research and scientific communication. Pharmacists can use these tools to stay updated, enhance the quality of their publications, optimise information management, and facilitate clinical decision-making.In conclusion, artificial intelligence is a powerful tool for hospital pharmacy, provided it is used responsibly and ethically.

QRGB+: Advanced QR Code Generator with RGB Color Method in Python to Expand Data Capacity

The present work entitled QRGB, consists of the development of an application in Python for the generation of QR codes using the additive color generation (RGB) method. This innovative method allows increasing the density of information stored in QR codes by using three color layers (red, green and blue), each representing a different set of data. QRGB offers an efficient and secure solution for storing and transmitting large amounts of information in limited spaces, significantly improving the capabilities of traditional black and white QR codes. By using three layers of colors, QRGB codes can store up to three times more information in the same space. This technique not only increases storage capacity but also improves information security, making it difficult to forge or manipulate the code. The overlay of multiple data layers allows redundancy to be implemented, increasing the robustness of the code against damage or reading errors. QRGBs are especially useful in applications that require the transmission of large amounts of data in limited spaces, such as in the packaging industry, digital business cards, and interactive advertising. Additionally, they have great potential in areas such as document and banknote security, where the authenticity and integrity of information are crucial. These points provide a solid foundation for understanding the innovation and advantages of colored QR codes (QRGB) compared to traditional QR codes, highlighting their applicability and potential in various sectors. This article presents a novel method for encoding and decoding information using a QRGB code, which involves the generation of three independent QR codes and their superimposition according to the additive color system (RGB). The research highlights the challenges encountered during the encoding and decoding processes due to the lack of specific libraries in Python, which required the creation of a custom solution using open source tools. The implementation takes advantage of Python and its libraries: qrcode[pil] to generate QR codes with the Pillow dependency for image manipulation, Pillow to open, manipulate and save different image formats, and opencv-python to perform tasks such as image processing and object detection. Despite facing issues with color mixing and accurate information retrieval, the proposed method demonstrates a significant increase in data density within a single QR code. Future work will focus on optimizing the algorithm and exploring potential applications in data security and high-density information storage. This Python script is designed to generate and decode QR codes with a logo overlay using a graphical user interface (GUI) built with Tkinter. The script combines several functionalities, such as creating QR codes, overlaying a logo, combining QR images of different colors, and manually decoding combined QR codes.

Information Retrieval in Friction Stir Welding of Aluminum Alloys by using Natural Language Processing based Algorithms

Information Retrieval in Friction Stir Welding of Aluminum Alloys by using Natural Language Processing based Algorithms

The main principles of the education of librarians of new qualification

The application of computers and the changing technology of library work reveal new professional demands for librarians, which necessitate changes in the education for librarianship and information work. The article addresses the theoretical questions of the content of education for the specialty "Librarianship and Bibliography" at the University of Vilnius. The offered complex of subjects is analyzed, and the main tendencies in the development of the curriculum are traced. The modification of library education is based on a new learning plan, which allows for the integration of individual subjects into blocks. This approach enables the selection of a central subject that forms the foundation of the new educational system and integrates separate blocks into one complex. In our opinion, this central subject is "Information Retrieval Systems." The main reasons for this choice, as well as the practical and theoretical advantages, are examined and justified.

Optimizing biomedical information retrieval with a keyword frequency-driven prompt enhancement strategy

BackgroundMining the vast pool of biomedical literature to extract accurate responses and relevant references is challenging due to the domain's interdisciplinary nature, specialized jargon, and continuous evolution. Early natural language processing (NLP) approaches often led to incorrect answers as they failed to comprehend the nuances of natural language. However, transformer models have significantly advanced the field by enabling the creation of large language models (LLMs), enhancing question-answering (QA) tasks. Despite these advances, current LLM-based solutions for specialized domains like biology and biomedicine still struggle to generate up-to-date responses while avoiding “hallucination” or generating plausible but factually incorrect responses.ResultsOur work focuses on enhancing prompts using a retrieval-augmented architecture to guide LLMs in generating meaningful responses for biomedical QA tasks. We evaluated two approaches: one relying on text embedding and vector similarity in a high-dimensional space, and our proposed method, which uses explicit signals in user queries to extract meaningful contexts. For robust evaluation, we tested these methods on 50 specific and challenging questions from diverse biomedical topics, comparing their performance against a baseline model, BM25. Retrieval performance of our method was significantly better than others, achieving a median Precision@10 of 0.95, which indicates the fraction of the top 10 retrieved chunks that are relevant. We used GPT-4, OpenAI's most advanced LLM to maximize the answer quality and manually accessed LLM-generated responses. Our method achieved a median answer quality score of 2.5, surpassing both the baseline model and the text embedding-based approach. We developed a QA bot, WeiseEule (https://github.com/wasimaftab/WeiseEule-LocalHost), which utilizes these methods for comparative analysis and also offers advanced features for review writing and identifying relevant articles for citation.ConclusionsOur findings highlight the importance of prompt enhancement methods that utilize explicit signals in user queries over traditional text embedding-based approaches to improve LLM-generated responses for specialized queries in specialized domains such as biology and biomedicine. By providing users complete control over the information fed into the LLM, our approach addresses some of the major drawbacks of existing web-based chatbots and LLM-based QA systems, including hallucinations and the generation of irrelevant or outdated responses.

Performance of the ChatGPT large language model for decision support in community pharmacy.

The aim of this study was to assess the ChatGPT-4 (ChatGPT) large language model (LLM) on tasks relevant to community pharmacy. ChatGPT was assessed with community pharmacy-relevant test cases involving drug information retrieval, identifying labelling errors, prescription interpretation, decision-making under uncertainty and multidisciplinary consults. Drug information on rituximab, warfarin, and St. John's wort was queried. The decision-support scenarios consisted of a subject with swollen eyelids and a maculopapular rash in a subject on lisinopril and ferrous sulfate. The multidisciplinary scenarios required the integration of medication management with recommendations for healthy eating and physical activity/exercise. The responses from ChatGPT for rituximab, warfarin, and St. John's wort were satisfactory and cited drug databases and drug-specific monographs. ChatGPT identified labeling errors related to incorrect medication strength, form, route of administration, unit conversion, and directions. For the patient with inflamed eyelids, the course of action developed by ChatGPT was comparable to the pharmacist's approach. For the patient with the maculopapular rash, both the pharmacist and ChatGPT placed a drug reaction to either lisinopril or ferrous sulfate at the top of the differential. ChatGPT provided customized vaccination requirements for travel to Brazil, guidance on management of drug allergies and recovery from a knee injury. ChatGPT provided satisfactory medication management and wellness information for a diabetic on metformin and semaglutide. LLMs have the potential to become a powerful tool in community pharmacy. However, rigorous validation studies across diverse pharmacist queries, drug classes and populations, and engineering to secure patient privacy will be needed to enhance LLM utility.

Jazz Trio Database: Automated Annotation of Jazz Piano Trio Recordings Processed Using Audio Source Separation

Recent advances in automatic music transcription have facilitated the creation of large databases of symbolic transcriptions of improvised music forms including jazz, where traditional notated scores are not normally available. In conjunction with music source separation models that enable audio to be “demixed” into separate signals for multiple instrument classes, these algorithms can also be applied to generate annotations for every musician in a performance. This can enable the analysis of interesting performer-level and ensemble-level features that have often been difficult to explore. To this end, we introduce Jazz Trio Database (JTD), a dataset of 44.5 h of jazz piano solos accompanied by bass and drums, with automatically generated annotations for each performer. These annotations consist of onset, beat, and downbeat timestamps, alongside MIDI for the piano soloist. Suitable recordings, broadly representative of the “straight-ahead” jazz style, were identified by scraping user-based listening and discographic data; source separation models were applied to isolate audio for each performer in the trio; annotations were generated by applying appropriate algorithms to both the separated and the mixed audio sources. Onset annotations generated by the pipeline achieved a mean F-measure of 0.94 when compared with ground truth annotations. We conduct several analyses of JTD, including with relation to swing and inter-performer synchronization. We anticipate that JTD will be useful in a variety of music information–retrieval tasks, including artist identification and expressive performance modeling. We have made JTD, including the annotations and associated source code, available at https://github.com/HuwCheston/Jazz-Trio-Database

Training of information retrieval in the State university of Vilnius: some contential and technological aspects of education in the field of librarianship and bibliography

The article deals with the problem of professional education of librarians at the University of Vilnius. The changing role of information, which is becoming one of the natural resources of the country, and the rapid development of computer technology reveal new professional demands for librarians. As a result of this tendency, teaching online bibliographical searching has become of great importance in the library education curriculum. Specific conditions of development and practical needs of libraries and information services, main traits, and opportunities of higher education in Lithuania are revealed. This makes it possible to create an original conception of automated information retrieval training. The problems of information retrieval are studied in subjects such as Librarianship, Bibliography, Information Retrieval Systems, Information, and Technical Aids for Library Work, which are based on a specially created training automated information retrieval system (AIRS). Three different kinds of connections between the revealed subjects are presented in a scheme and commented upon. The choice of education technology is discussed. The main forms are various practical studies, realized on the basis of AIRS. These also help overcome the psychological barrier that arises when working with computers.

A Study on the Integration of Big Data With Information Retrieval Technology in the Construction of Translation Talent Pools

This paper conducts a corresponding study on the construction of a translation talent pool internally through the context of information retrieval technology. It first discusses the current state of development of information retrieval technology in various countries in the present era and the current social development of information retrieval technology. A model of the system is constructed by basing it on information retrieval technology. The system model of information retrieval technology combined with the optimisation problems associated with translation talent pools is also investigated, incorporating a factorisation algorithm. The results of the study show that the system model of big data combined with information retrieval technology has good application in concrete practical applications after modelling and performing internal upgrading.

Spatial intelligence and contextual relevance in AI-driven health information retrieval

The evolution of large language models (LLMs) has already significantly influenced online health information retrieval. As these models gain more widespread use, it is important to understand their ability to contextualize responses based on spatial and geographic information. This study investigates whether LLMs can vary responses based on geographic and spatial context. Using a structured set of prompts submitted to ChatGPT, responses were analyzed to discern patterns based on prompt question and geographic identifiers included in queries. The analysis used word frequency analysis and bidirectional encoder representations from transformers (BERT) embeddings to evaluate the variation in responses concerning geographic specificity. The results provide some evidence that LLMs can generate geographically tailored responses when the query specifies such a need, thereby supporting localized information retrieval. Moreover, prompt responses exhibit an association between spatial distance and word frequency/sentence embedding differences between texts. This result suggests a nuanced representation of spatial information, which could impact user experience by providing more relevant health information based on the user's location. This study lays the groundwork for further exploration into the spatial intelligence of LLMs and their impact on the accessibility of health information online.

Comparative Evaluation of Pre-Trained Language Models for Biomedical Information Retrieval.

Finding relevant information in the biomedical literature increasingly depends on efficient information retrieval (IR) algorithms. Cross-Encoders, SentenceBERT, and ColBERT are algorithms based on pre-trained language models that use nuanced but computable vector representations of search queries and documents for IR applications. Here we investigate how well these vectorization algorithms estimate relevance labels of biomedical documents for search queries using the OHSUMED dataset. For our evaluation, we compared computed scores to provided labels by using boxplots and Spearman's rank correlations. According to these metrics, we found that Sentence-BERT moderately outperformed the alternative vectorization algorithms and that additional fine-tuning based on a subset of OHSUMED labels yielded little additional benefit. Future research might aim to develop a larger dedicated dataset in order to optimize such methods more systematically, and to evaluate the corresponding functions in IR tools with end-users.

Help-Seeking Situations Related to Visual Interactions on Mobile Platforms and Recommended Designs for Blind and Visually Impaired Users.

While it is common for blind and visually impaired (BVI) users to use mobile devices to search for information, little research has explored the accessibility issues they encounter in their interactions with information retrieval systems, in particular digital libraries (DLs). This study represents one of the most comprehensive research projects, investigating accessibility issues, especially help-seeking situations BVI users face in their DL search processes. One hundred and twenty BVI users were recruited to search for information in six DLs on four types of mobile devices (iPhone, iPad, Android phone, and Android tablet), and multiple data collection methods were employed: questionnaires, think-aloud protocols, transaction logs, and interviews. This paper reports part of a large-scale study, including the categories of help-seeking situations BVI users face in their interactions with DLs, focusing on seven types of help-seeking situations related to visual interactions on mobile platforms: difficulty finding a toggle-based search feature, difficulty understanding a video feature, difficulty navigating items on paginated sections, difficulty distinguishing collection labels from thumbnails, difficulty recognizing the content of images, difficulty recognizing the content of graphs, and difficulty interacting with multilayered windows. Moreover, corresponding design recommendations are also proposed: placing meaningful labels for icon-based features in an easy-to-access location, offering intuitive and informative video descriptions for video players, providing structure information about a paginated section, separating collection/item titles from thumbnail descriptions, incorporating artificial intelligence image/graph recognition mechanisms, and limiting screen reader interactions to active windows. Additionally, the limitations of the study and future research are discussed.

Multi-dimensional feature fusion-based expert recommendation in community question answering

PurposeCommunity question answering (CQA) platforms play a significant role in knowledge dissemination and information retrieval. Expert recommendation can assist users by helping them find valuable answers efficiently. Existing works mainly use content and user behavioural features for expert recommendation, and fail to effectively leverage the correlation across multi-dimensional features.Design/methodology/approachTo address the above issue, this work proposes a multi-dimensional feature fusion-based method for expert recommendation, aiming to integrate features of question–answerer pairs from three dimensions, including network features, content features and user behaviour features. Specifically, network features are extracted by first learning user and tag representations using network representation learning methods and then calculating questioner–answerer similarities and answerer–tag similarities. Secondly, content features are extracted from textual contents of questions and answerer generated contents using text representation models. Thirdly, user behaviour features are extracted from user actions observed in CQA platforms, such as following and likes. Finally, given a question–answerer pair, the three dimensional features are fused and used to predict the probability of the candidate expert answering the given question.FindingsThe proposed method is evaluated on a data set collected from a publicly available CQA platform. Results show that the proposed method is effective compared with baseline methods. Ablation study shows that network features is the most important dimensional features among all three dimensional features.Practical implicationsThis work identifies three dimensional features for expert recommendation in CQA platforms and conducts a comprehensive investigation into the importance of features for the performance of expert recommendation. The results suggest that network features are the most important features among three-dimensional features, which indicates that the performance of expert recommendation in CQA platforms is likely to get improved by further mining network features using advanced techniques, such as graph neural networks. One broader implication is that it is always important to include multi-dimensional features for expert recommendation and conduct systematic investigation to identify the most important features for finding directions for improvement.Originality/valueThis work proposes three-dimensional features given that existing works mostly focus on one or two-dimensional features and demonstrate the effectiveness of the newly proposed features.

Advancing continual lifelong learning in neural information retrieval: Definition, dataset, framework, and empirical evaluation

Continual learning refers to the capability of a machine learning model to learn and adapt to new information, without compromising its performance on previously learned tasks. Although several studies have investigated continual learning methods for neural information retrieval (NIR) tasks, a well-defined task definition is still lacking, and it is unclear how typical learning strategies perform in this context. To address this challenge, a systematic task definition of continual NIR is presented, along with a multiple-topic dataset that simulates continuous information retrieval. A comprehensive continual neural information retrieval framework consisting of typical retrieval models and continual learning strategies is then proposed. Empirical evaluations illustrate that the proposed framework can successfully prevent catastrophic forgetting in neural information retrieval and enhance performance on previously learned tasks. The results also indicate that embedding-based retrieval models experience a decline in their continual learning performance as the topic shift distance and dataset volume of new tasks increase. In contrast, pretraining-based models do not show any such correlation. Adopting suitable learning strategies can mitigate the effects of topic shift and data augmentation in continual neural information retrieval.

PubMed Retrieval with RAG Techniques.

This study explores the application of Retriever-Augmented Generation (RAG) in enhancing medical information retrieval from the PubMed database. By integrating RAG with Large Language Models (LLMs), we aim to improve the accuracy and relevance of medical information provided to healthcare professionals. Our evaluation on a labeled dataset of 1,000 queries demonstrates promising results in answer relevance, while highlighting areas for improvement in groundedness and context relevance.

Integrating AI-Generated Summaries of Medication Leaflets into a Mobile Application for Medication Management.

Effective medication management poses significant challenges, particularly when navigating multiple medications with intricate dosages and schedules. This paper presents a prototype mobile application to streamline information retrieval from dense medication leaflets. By utilizing automated information extraction based on large language models, the application seamlessly retrieves pertinent details from the Austrian medicinal product index upon scanning the medication package. This extracted information is organized and displayed within the app, ensuring clarity and accessibility for users. In addition to this core functionality, the application offers a suite of features tailored to facilitate effective medication management. By integrating comprehensive medication information with practical medication management tools, the application empowers users to navigate complex medication regimes with confidence and ease.