User Query Research Articles

KnowVID-19: A Knowledge-Based System to Extract Targeted COVID-19 Information from Online Medical Repositories

We present KnowVID-19, a knowledge-based system that assists medical researchers and scientists in extracting targeted information quickly and efficiently from online medical literature repositories, such as PubMed, PubMed Central, and other biomedical sources. The system utilizes various open-source machine learning tools, such as GROBID, S2ORC, and BioC to streamline the processes of data extraction and data mining. Central to the functionality of KnowVID-19 is its keyword-based text classification process, which plays a pivotal role in organizing and categorizing the extracted information. By employing machine learning techniques for keyword extraction—specifically RAKE, YAKE, and KeyBERT—KnowVID-19 systematically categorizes publication data into distinct topics and subtopics. This topic structuring enhances the system’s ability to match user queries with relevant research, improving both the accuracy and efficiency of the search results. In addition, KnowVID-19 leverages the NetworkX Python library to construct networks of the most relevant terms within publications. These networks are then visualized using Cytoscape software, providing a graphical representation of the relationships between key terms. This network visualization allows researchers to easily track emerging trends and developments related to COVID-19, long COVID, and associated topics, facilitating more informed and user-centered exploration of the scientific literature. KnowVID-19 also provides an interactive web application with an intuitive, user-centered interface. This platform supports seamless keyword searching and filtering, as well as a visual network of term associations to help users quickly identify emerging research trends. The responsive design and network visualization enables efficient navigation and access to targeted COVID-19 literature, enhancing both the user experience and the accuracy of data-driven insights.

ROI constrained optimal online allocation in sponsored search

Sponsored search plays a major role in the revenue contribution of e-commerce platforms. Advertising systems are designed to maximize platform revenue, but other goals also need to be considered, such as user experience, advertiser utility, and how to achieve the long-term revenue goal. A key component of a sponsored search system is online allocation, which makes real-time decisions to match users’ search requests with relevant ad campaigns to maximize platform revenue within constraints such as campaign budgets. Although much progress has been made, most of the research work on allocation problem has focused on satisfying guaranteed deals for display ads, and those challenges for allocation problems in sponsored search are not properly addressed. In this paper, we develop a framework to solve the large-scale sponsored search ad allocation problem, consisting of two main parts. One is an optimization problem solved offline by a parameter-server based architecture, and the other is an online strategy to alleviate the conflict with the auction mechanism during online service. Comprehensive offline evaluation on real production data and online A/B testing on real production system have been made. The experimental results demonstrate that through better allocating user queries to appropriate ads, the proposed model can significantly increase the platform’s revenue without sacrificing advertisers’ ROI.

VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval

The relations expressed in user queries are vital for cross-modal information retrieval. Relation-focused cross-modal retrieval aims to retrieve information that corresponds to these relations, enabling effective retrieval across different modalities. Pre-trained networks, such as Contrastive Language-Image Pre-training networks, have gained significant attention and acclaim for their exceptional performance in various cross-modal learning tasks. However, the Vision Transformer (ViT) used in these networks is limited in its ability to focus on image region relations. Specifically, ViT is trained to match images with relevant descriptions at the global level, without considering the alignment between image regions and descriptions. This article introduces VITR, a novel network that enhances ViT by extracting and reasoning about image region relations based on a local encoder. VITR is comprised of two key components. Firstly, it extends the capabilities of ViT-based cross-modal networks by enabling them to extract and reason with region relations present in images. Secondly, VITR incorporates a fusion module that combines the reasoned results with global knowledge to predict similarity scores between images and descriptions. The proposed VITR network was evaluated through experiments on the tasks of relation-focused cross-modal information retrieval. The results derived from the analysis of the Flickr30K, MS-COCO, RefCOCOg, and CLEVR datasets demonstrated that the proposed VITR network consistently outperforms state-of-the-art networks in image-to-text and text-to-image retrieval.

BBBper: A Machine Learning-based Online Tool for Blood-Brain Barrier (BBB) Permeability Prediction.

Neuronal disorders have affected more than 15% of the world's population, signifying the importance of continued design and development of drugs that can cross the Blood-Brain Barrier (BBB). BBB limits the permeability of external compounds by 98% to maintain and regulate brain homeostasis. Hence, BBB permeability prediction is vital to predict the activity of a drug-like substance. Here, we report about developing BBBper (Blood-Brain Barrier permeability prediction) using machine learning tool. A supervised machine learning-based online tool, based on physicochemical parameters to predict the BBB permeability of given chemical compounds was developed. The user-end webpage was developed in HTML and linked with back-end server by a python script to run user queries and results. BBBper uses a random forest algorithm at the back end, showing 97% accuracy on the external dataset, compared to 70-92% accuracy of currently available web-based BBB permeability prediction tools. The BBBper web tool is freely available at http://bbbper.mdu.ac.in.

From Traditional to Digital: Evaluating the Role of Spirituality in Mental Health and Therapy

The increasing number of mental health issues has obliged us to find new methods that are not only innovative but also so easy that they can be used by almost everybody. The given paper examines the progress and effect of the mental health and life- assisting chat-bot. The main idea of the chat-bot incorporates elements from the Bhagavad Gita, the ancient spiritual manual. Information was collected to measure the public's view of introducing spirituality into the traditional treatment, the results reveal that the majority back such a venture. A study (n=51) was conducted, and respondents were asked questions about their age, religion, opinion on spirituality and mental health, and choice for which method online therapy or traditional therapy. It was found that out of all the respondents, (80.4% aged 16-25) there was a large majority (88.2%) that mentioned the spiritual aspect of mental well- being. There were a lot (most responses were YES) of them have been into spiritual exercises when they faced the difficulties, they still believe that it still could be personalized intervention to use. Even as traditional therapy is the main option (70.6%), a significant number of respondents (29.4%) still feel comfortable with online help. Those research counterparts that focus on the role of technology in mental health improvements which tend to look to the public for a response, are the ones that discuss the chance for the Bhagavad-Gita chatbot as a supplementary tool. The proposed chatbot will make use of Natural Language Processing (NLP) in understanding a user query and generating an answer through reference to Bhagavad Gita. Key Words: Bhagavad Gita, Mental health, Chatbot, Spiritual therapy, Technology-assisted therapy

Implementation of Chatbot Artificial Intelligence in a Company Website to Improve Customer Service Automatically Using the TF-IDF Method

In today's digital age, improving customer service is one of the keys to business success. Successfully retaining and attracting new customers is a challenge that must be faced. The application of chatbot technology powered by artificial intelligence (AI) on business websites has been proven to provide more efficient and responsive customer service. This research aims to develop and implement an AI chatbot that uses the TF-IDF (Term Frequency-Inverse Document Frequency) method to automatically understand and answer customer queries. The TF-IDF method is used to extract key features from the text of customer questions and match them with the most relevant answers in the database. The results of implementing this AI chatbot showed a significant improvement in the speed and quality of customer service responses, thus helping to improve customer satisfaction and company performance. This research provides valuable insights for businesses looking to integrate AI technology into their customer service strategy.

Management and Performance Program Chatbot: A Use Case of Large Language Model in the Federal Public Sector in Brazil

Governments are facing the benefits and perils of recent developments in artificial intelligence. One key objective is using AI to enhance the efficiency and effectiveness of their public service provision. While academic research has examined these advances, there is a lack of empirical evidence regarding user experiences. This paper explores the initial results of using a chatbot based on a Large Language Model (LLM) to address user queries about the Management and Performance Program (PGD). Survey analysis demonstrated that ChatPGD is likely to reduce program-related response time and increase effectiveness. However, the initial tests indicated a need to refine response algorithms to detect and mitigate potential biases and to strengthen the system infrastructure to support new enhancements. This paper examines the chatbot's application in harnessing government databases, highlighting the potential benefits, challenges, and perspectives of embedding AI and LLMs in public service delivery. The insights can support the development of other public service LLMs.

Exploring the digital gray zone of online medicinal markets emerging from search

AbstractThis explorative study investigates the emergence of gray zone markets from search engines amidst the global expansion of online markets. With the analytical approach of infrastructural inversion, we examine how the search infrastructure constructs access to a gray zone market including both authorized online pharmacies and unauthorized vendors. Using Sweden and Google Search as a case, we explore the online presence of three products (vitamin D, paracetamol, and Viagra), through search engine result page analysis, web crawling, and network analysis. Infrastructural inversion unveils the typically invisible mechanisms of search engines, considering user queries, algorithmic priorities, SEO practices, and pharmacy regulations. We find gray zones only emerge in searches for erectile disfunction medicinal products and information, where unauthorized vendors successfully competed for visibility in search engine rankings. A complex web of conditions can steer consumers toward gray zone markets, complicating the access to safe and regulated medicinal products. This can expose individuals to risks associated with unverified medicinal products, but also challenges the integrity of the online health information infrastructure.

Correlation-aware Cross-modal Attention Network for Fashion Compatibility Modeling in UGC Systems

Empowered by the continuous integration of social multimedia and artificial intelligence, the application scenarios of information retrieval (IR) progressively tend to be diversified and personalized. Currently, User-Generated Content (UGC) systems have great potential to handle the interactions between large-scale users and massive media contents. As an emerging multimedia IR, Fashion Compatibility Modeling (FCM) aims to predict the matching degree of each given outfit and provide complementary item recommendation for user queries. Although existing studies attempt to explore the FCM task from a multimodal perspective with promising progress, they still fail to fully leverage the interactions between multimodal information or ignore the item-item contextual connectivities of intra-outfit. In this paper, a novel fashion compatibility modeling scheme is proposed based on Correlation-aware Cross-modal Attention Network. To better tackle these issues, our work mainly focuses on enhancing comprehensive multimodal representations of fashion items by integrating the cross-modal collaborative contents and uncovering the contextual correlations. Since the multimodal information of fashion items can deliver various semantic clues from multiple aspects, a modality-driven collaborative learning module is presented to explicitly model the interactions of modal consistency and complementarity via a co-attention mechanism. Considering the rich connections among numerous items in each outfit as contextual cues, a correlation-aware information aggregation module is further designed to adaptively capture significant intra-correlations of item-item for characterizing the content-aware outfit representations. Experiments conducted on two real-world fashion datasets demonstrate the superiority of our approach over state-of-the-art methods.

Emotional dialogue generation model of electronic commerce intelligent customer service based on topic expansion

Current electronic commerce (e-commerce) customer service systems often rely on retrieval-based methods, resulting in impersonal and emotionally flat responses. These systems struggle to handle diverse expressions and emotional nuances in user queries, leading to poor user experience. In this paper, we applied artificial intelligence techniques, notably the Gated Recurrent Unit model, to generate emotionally resonant dialogues in e-commerce customer service systems. We integrate intent recognition, emotion recognition, and topic expansion for accurate intent identification and nuanced responses. The model is trained on a customer service dataset from Jing Dong, a leading Chinese e-commerce platform. Through extensive experiments, we conducted comparative analyses against benchmark model Gated Recurrent Unit neural network. The results demonstrate that our model significantly outperforms existing approaches, achieving fluency, rationality, and emotionality scores of 62%, 58% and 61% respectively. These findings indicate that our approach generates responses with greater consistency to user intent and richer emotional content. The significance of these results lies in their potential to enhance user experience in e-commerce customer service interactions by providing more personalized and emotionally resonant automated responses.

LLM Based Chatbot for Farm-to-Fork Blockchain Traceability Platform

Blockchain technology has been used with great effect in farm-to-fork traceability projects. However, this technology has a steep learning curve when it comes to its user interface. To minimize this difficulty, we created a solution based on a Large Language Model (LLM) conversational agent. Our implementation, starting with an existing knowledge base that is prepared and processed with an embedding model to be stored in a vector database, follows a Retrieval-Augmented Generation (RAG) approach. Other non-textual media like images and videos are aggregated with the embeddings to enrich the user experience. User queries are combined with a proximity search in the vector database and feed into an LLM that considers the conversation history with the user in its replies. Given the asynchronous nature of these models, we implemented a similarly asynchronous scheme using Server-Sent Events that deliver the models’ replies to a UI that supports multimodal media types such as images and videos by providing the visualization of these resources. The end solution allows users to interact with advanced technologies using a natural language interface; this in turn empowers food traceability projects to overcome their natural difficulty in engaging early adopters.

Indexing for Fine Arts Monographs: A Comparison Between User Queries and Controlled Vocabularies

ABSTRACTPrior research suggested the empirical approach to indexing for fine arts based on users' search queries. This study examined the characteristics of user queries submitted to the library catalog of a fine arts academy, and compared users' search terms with controlled vocabularies to assess their levels of matching. Based on search‐log analysis, this study identified eight categories of user queries and 10 subcategories, indicating that the information needs of the fine arts community are diverse in language and culture and focus on named entities, disciplines, and various types and levels of fine arts. The mapping between user queries and controlled vocabularies found that around 20% of user search terms were non‐matching. Based on the findings, this study provided suggestions for improving the search functions of library catalogs and enhancing controlled vocabularies to support the retrieval of fine arts monographs.

ADCMDES: Design of an augmented cross-domain collaborative recommendation model using novel distance metric and ensemble stratification

Collaborative recommendation involves leveraging information from one entity to suggest attributes of other entities through pattern analysis. These models are invaluable for understanding data behaviour’s impact on related entities. Researchers propose various pattern recognition and correlation models, employing distance metrics like Jaccard, Cosine, etc., to estimate correlations between user queries and recommendation datasets. However, these models become less efficient as dataset size increases due to exponential correlation estimation delays. To enhance scalability while retaining recommendation quality, a new approach is introduced: ADCMDES. This novel augmented cross-domain collaborative model employs a hybrid distance metric and ensemble stratification for dataset pruning. It operates semi-supervisedly, requiring information about the entities being collaborated upon. This data is used to cluster similar collaborative entities, producing a condensed cluster with greater relevancy to user queries. Utilizing word2vec, records are transformed into features for an ensemble classification engine. The resultant model categorizes user input, directing it to the most relevant cluster. Entries within this cluster are ranked using a hybrid metric amalgamating 18 distance measures, enhancing correlation between input queries and recommendations. In testing, ADCMDES exhibited 15% better accuracy, 8% better precision, 9% better recall, and 3% lower RMSE compared to standard models across datasets. While some delay is introduced due to ensemble classification and augmented feature pooling, this doesn't considerably affect long-term recommendation performance and can be mitigated through parallel processing and redundancy reduction techniques.

Application of a Question Answering System in the Ontology-Based Health Domain and Question Templates to Improve the Quality of Answers

Developing an effective Question Answering System (QAS) to address a wide range of health-related inquiries presents a significant challenge. This study introduces an innovative approach using an ontology-based QAS within the health domain, leveraging the Resource Description Framework (RDF) and SPARQL query language. By utilizing ontology, the system can more accurately map health concepts, improving the relevance and precision of its responses. Additionally, the incorporation of structured Question Templates enhances the system’s ability to understand and respond to diverse user queries. The system's performance was evaluated using Black Box Testing, which demonstrated that it consistently provides accurate and relevant answers. The system achieved a Mean Average Precision (MAP) of 79.6%, indicating its potential to effectively address a broad spectrum of health issues.

IntAct Database for Accessing IMEx's Contextual Metadata of Molecular Interactions.

The International Molecular Exchange Consortium (IMEx) has evolved into a vital partnership of open resources dedicated to curating molecular interaction data from the scientific literature. This consortium, which includes IntAct, MINT, MatrixDB, and DIP, is a collaborative effort with a central mission of aggregating detailed molecular interaction experimental evidence in a machine-readable format, supported by controlled vocabularies and standard ontologies. The IntAct molecular interaction database (www.ebi.ac.uk/intact), as an IMEx partner, serves as a valuable portal for accessing IMEx data through user-friendly search options and an array of interactive filters. The resource currently hosts an extensive repository of 1,293,508 binary interactions meticulously captured from 75,098 experiments documented in 23,366 publications (as of the February 2024 release), with this corpora being added to by regular data releases. IMEx curation policy has consistently prioritized a fine-grained data and curation model, with a focus on capturing the relevant experimental details essential for interpreting molecular interaction data effectively. Our curation process is designed to support the generation of interactomes tailored to contexts such as disease-specific or tissue-/cell-type-specific interactomes. These interactions are ranked according to a scoring system based on the Proteomics Standard Initiative Molecular Interaction (PSI MI) standards. This scoring system allows users to assess the degree of confidence in binary interactions, enhancing the value of the data. The resource provides insights into the nature of relationships among interacting partners as defined by the experimental setup and the associated biological context. Interactive filters enable users to navigate these rich, multilayered data, promoting a deeper understanding of biological complexity. Additionally, the IntAct website fosters the creation of networks for collaborative analyses by the scientific community. The recent transformation of the IntAct website, supported by a graph-type database, empowers users to execute custom queries tailored to their specific research interests. This article illustrates the diverse levels of annotations available for interactions and the multiple search options at users' disposal to access data of interest. © 2024 European Molecular Biology Laboratory, European Bioinformatics Institute. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Using Quick Search, network visualization, and filters Support Protocol: Accessing fine annotations from intact: Unlocking the molecular details Alternate Protocol: Using batch search: Querying multiple interactors Basic Protocol 2: Using advanced search: Precision and customization.

Harnessing AI for Enhanced Searching in Digital Libraries: Transforming Research Practices

The application of Artificial Intelligence (AI) technologies in digital libraries is changing the paradigm in which users search and interact with digital content. This article is focused on how the use of AI technologies improves the search in digital libraries, demonstrating the benefits of such technologies in overcoming the challenges associated with formulation of query, information retrieval, and end user usage. Most search engine systems face the problems of user queries, which are inherent in online searches. Many user queries are vague, imprecise or ambiguous with regards to the context and as a result lead to less than satisfactory search results. AI technologies such as Natural Language Processing (NLP) and Machine Learning (ML) solve this challenge effectively as they enhance comprehension of queries, contextual understanding, and relevance of the results returned. With the capabilities of NLP incorporated in search engines, search queries which are in the form of natural language can be understood and executed which leads to efficiency in targeting the information needed. Comprehensive restructuring of standard information systems is used by computer learning algorithms for searches by inference and instills usage in users. This study also examines the place of AI in query formulation and the different ways it can be employed; fully automated, semi-automated and/or manually so that the users are less faced with the challenges that are usually present during the query formulation process. Such increases in the level of difficulty and scope of information retrieval suggest that search AI improved the scenario.

Next-Gen Database Queries: AI-Driven Natural Language Interface for MongoDB

This paper present an novel concept to query MongoDB database using NLP and Large Language Model (LLM). It is called LLM Based MongoDB Querying System through which users can search in MongoDB databases just by using simple words of English language rather than using complex language queries. To help improve the ai quality we use OpenAI’s LLM to parse the user queries and create correct MongoDB queries themselves. In a large-scale experiment, system is able to classify with an average of 95 percentage accuracy. The findings of this research are important forthe database querying research and might be beneficial for multiple domains. This research is valuable, because our system can help ordinary users become more fluent in database operations and make working with databases more efficient.

Optimization model for vehicular network data queries in edge environments

As the Internet of Vehicles advances, the demand for timely data acquisition by vehicle users continues to escalate, albeit confronted with the challenge of excessive data retrieval latency. The emergence of edge computing provides technical support for the development of vehicular networks by caching data in advance to reduce data acquisition latency. Therefore, how to effectively cache and query data becomes a key issue in addressing the timeliness of data acquisition in vehicular networks. In this paper, we investigate an efficient query optimization model to minimize data acquisition latency. Firstly, based on the distribution of data query frequencies across different servers, we propose an edge collaborative caching strategy using a tabu search algorithm. This strategy prioritizes high-traffic data by finding two optimal storage nodes for each high-traffic data in descending order of data popularity, ensuring a backup within the collaborative domain for each data segment. This not only reduces data transmission latency between nodes during task execution but also prevents single-point failures. Secondly, we deploy cuckoo filters on edge nodes to enable rapid localization of cached data nodes when users query data, thus reducing data processing latency. Finally, simulation results demonstrate that the proposed query optimization model outperforms other schemes in terms of average data query latency.

Dataset Expansion with Pseudo-Labeling: Case Study for Optimizing Chatbot Intent Recognition

Purpose of the study: This study presents an approach for improving the performance of natural language processing (NLP) models in pseudo-labeling tasks, with a particular focus on enhancing chatbot model intent recognition for business use cases. Methodology: The employed case study approach explores the pseudo-labeling technique and demonstrates a practical and efficient way to iteratively expand the original set of labeled data for the purpose of refining model training to achieve superior intent recognition accuracy in chatbots. Main Findings: The approach results in notable increases in macro-averaged F1 score and overall accuracy, particularly by iteratively re-training the model with progressively larger datasets. While enhancing the model's ability to generalize through difficult cases was effective, the study found that incorporating a full range of examples, including easy ones, yielded the best results. This comprehensive approach made the model better suited for real-world applications. Applications of the study: As chatbots are increasingly deployed in various sectors, including business, customer service, healthcare, and education, it becomes crucial for research to examine their long-term impact, scalability, and adaptability to ensure their effectiveness and sustainability in diverse contexts. Therefore, building more accurate chatbots, capable of understanding a wide range of user intents, is particularly valuable in real-world applications where chatbots need to respond to diverse, often complex and unpredictable user queries. Novelty/Originality of the study: Unlike traditional approaches, this study introduces a novel strategy of filling low-density regions in the dataset with pseudo-labels, allowing the model to better separate classes and handle semantically similar but varied messages. These advancements contribute to a more effective and scalable chatbot solution across diverse industries.

Transforming User Experience (UX) through Artificial Intelligence (AI) in Interactive Media Design

This paper discusses the application and advantages of artificial intelligence technology in digital media interactive product design. Firstly, the development background of artificial intelligence technology and its promoting effect on design innovation is introduced, and the application of new technologies, such as generative adversarial networks in art creation and design personalization, is definitely analyzed. It then explores in detail the ability of AI to break traditional constraints in interactive design, innovate design, and optimize user experience, especially in digital media. Finally, the case study of Microsoft Cortana shows the method of classifying and processing user queries by machine learning system and its experimental results. The research of this paper provides the theoretical basis and empirical support for the application of artificial intelligence technology in the future interactive design of digital media and has important academic and practical significance.