User Query Research Articles

A Study on the Effectiveness of Using Social Media for Organizational Reputation Management in the Telecommunications Industry in Zambia. A case of Zamtel

The aim of this study was to assess the effectiveness of social media usage for organizational reputation management. This study employed a descriptive quantitative research design with a population of 150 employees working at Zamtel's head office in Lusaka. A Yamane formula was used to randomly select a sample of 109 employees for data collection. The researcher designed a questionnaire for this purpose, and descriptive analysis was conducted using SPSS. The study revealed that 68% of respondents believe social media is effective in managing an organization's reputation in Zambia. Zamtel has been positively impacted by social media in the past years, particularly in increasing responsiveness to customer queries and enhancing brand image, highlighting the need for the organization to continue focusing on its online presence and implement strategies to manage its reputation. The most common types of social media strategies used for reputation management by Zamtel include building brand awareness and creating engaging content, mostly through Facebook. The research also revealed challenges faced by Zamtel in using social media for organization reputation management, with a lack of resources and poor message design being the most significant challenges. The study recommends, among other things, that by establishing a social media policy, monitoring online conversations, engaging with followers, creating shareable content, utilizing influencer marketing, and responding to negative feedback, businesses can build a positive reputation online and enhance their brand image.

Chatbot Building with BERT for E-Commerce

Abstract: Building a chatbot powered by BERT (Bidirectional Encoder Representations from Transform-ers) involves leveraging its pre-trained language understanding abilities to create an interface that mimics human conversation. Developed by Google, BERT marks a significant advancement in natural language processing (NLP), showcasing remarkable performance across a range of tasks. In the era of increasing artificial intelligence (AI) adoption, chatbots have emerged as crucial tools for engaging users, particularly on mobile platforms where they adapt to different contexts and communication modes, including text and voice. BERT's bidirectional architecture allows it to grasp word meanings within their surrounding context, thanks to its extensive pre-training on vast textual datasets. Fine-tuning BERT for chatbot applications involves training it on a dataset containing user queries paired with suitable responses, with annotations indicating response appropriateness. Tokenization, a crucial preprocessing step, involves breaking down sentences into smaller tokens to aid BERT's processing efficiency. The chatbot architecture integrates BERT, potentially incorporating additional layers to enhance context understanding and response generation. Following this, the model undergoes training using fine-tuned BERT on the prepared dataset, with adjustments made to hyperparameters for optimal performance. Evaluation of the chatbot typically involves testing it on a validation set or through interactive sessions to assess its effectiveness. Any necessary refinements to the architecture or finetuning process are guided by performance analysis. Ultimately, deploying the chatbot involves seamless integration into realworld platforms such as web or mobile applications, enabling smooth interaction between users and the chatbot across various scenarios, all while prioritizing originality and integrity in the development process.

COLLEGE ENQUIRY CHATBOT

A chatbot is software that is used to interact between a computer and a human in a natural language, as humans chat. Chatbots engage in conversation with users in place of humans and respond to them. The goal of this report on chatbots was to resemble a human being in the way they interact, trying to make the user think he is chatting with another human being. The chatbot application helps students access university-related information from anywhere with an internet connection. This system reduces the work of college administration providing information to students and reduces the workload on the staff to answer all the students' queries. This project aims to develop a college inquiry chatbot that answers any queries posted by students, like college details, course-related questions, location of the college, fee structure, etc. The College Enquiry Chatbot project is built using deep learning algorithms that analyze user’s queries and understand the users' messages. This system is a web application that returns answers to queries. Any individual can simply query the bot. The answers are appropriate to the user's query. The system allows users to query any college-related activities. The user does not have to personally go to the college for an inquiry. The system analyses the question and then answers it for the user. Through the suggestion box, users can also provide suggestions. The system replies using an effective graphic user interface, which implies that a real person is talking to the user. KEYWORDS: Chat bot, Artificial Intelligence, Enquiry, Response, Query.

Exploratory and directed search strategies at a social science data archive

Researchers need to be able to find, access, and use data to participate in open science. To understand how users search for research data, we analyzed textual queries issued at a large social science data archive, the Inter-university Consortium for Political and Social Research (ICPSR). We collected unique user queries from 988,475 user search sessions over four years (2012-16). Overall, we found that only 30% of site visitors entered search terms into the ICPSR website. We analyzed search strategies within these sessions by extending existing dataset search taxonomies to classify a subset of the 1,554 most popular queries. We identified five categories of commonly-issued queries: keyword-based (e.g., date, place, topic); name (e.g., study, series); identifier (e.g., study, series); author (e.g., institutional, individual); and type (e.g., file, format). While the dominant search strategy used short keywords to explore topics, directed searches for known items using study and series names were also common. We further distinguished exploratory browsing from directed search queries based on their page views, refinements, search depth, duration, and length. Directed queries were longer (i.e., they had more words), while sessions with exploratory queries had more refinements and associated page views. By comparing search interactions at ICPSR to other natural language interactions in similar web search contexts, we conclude that dataset search at ICPSR is underutilized. We envision how alternative search paradigms, such as those enabled by recommender systems, can enhance dataset search.

A comprehensive overview of the application of artificial intelligence in language learning

With the rapid advancement of artificial intelligence, AI technology has made significant progress in the field of language. Machine translation has become the dominant method, replacing manual translation due to its convenience and speed. This article will discuss three different aspects: translation, information retrieval, and language artificial intelligence. In the translation section, three distinct translation models will be analyzed, using Google Translate as a foundation. These models have transformed the translation industry and improved accuracy and efficiency. In the information retrieval section, the differences between semantic search involving AI and traditional keyword-based search techniques will be explored. Semantic search, driven by AI, provides more accurate and relevant search results by understanding the context and intent behind user queries. The impact of these advancements on search engine optimization (SEO) practices will also be discussed. Furthermore, the article will delve into the types of speech recognition and classify speech recognition technologies. Finally, the article will summarize the entire content and provide an outlook on future developments.

Proxy Re-Encryption for Secure Data Sharing with Blockchain in Internet of Medical Things

The Internet of Medical Things (IoMT) is crucial in our daily health monitoring and assisting doctors in treatment. However, the existing schemes mainly use cloud servers to solve the storage of large amounts of data generated by smart devices, ignoring the guarantee mechanism of ciphertext integrity, which may result in data being tampered with or replaced in data sharing. To address this issue, we propose a secure data sharing scheme named Proxy Re-Encryption for Secure Data Sharing with Blockchain in Internet of Medical Things (PRE-IoMT). Specifically, we propose a new proxy re-encryption data sharing approach by introducing identity hash during the key generation phase to realize the binding of public key and user identity, thus enhancing the security of data sharing in PRE-IoMT. Moreover, we adopt BlockChain transactions to design a pairing function ciphertext check mechanism, which can effectively prevent the ciphertext stored in the cloud server from being tampered with. We add the user to the accumulator by invoking the BlockChain smart contract to realize the management and fast query of users. Finally, we conduct the performance analysis experiments on the four-stage computation of proxy re-encryption, communication overhead, storage overhead, transmission delay, and the delay of BlockChain transactions, compared with existing schemes, our scheme improves the computation efficiency of encryption, re-encryption, decryption, and re-decryption by about 23.8%, 71.4%, 48%, and 15.3% respectively. The security proof also exhibits that PRE-IoMT can resist IND-ID-CPA.

Evaluation of Natural Language Processing Techniques for Information Retrieval

Purpose: The main objective of the study was to investigate the evaluation of Natural Language Processing techniques for information retrieval.
 Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library.
 Findings: The findings reveal that there exists a contextual and methodological gap relating to Natural Language Processing techniques for information retrieval. Preliminary empirical review revealed that NLP methods significantly improved the accuracy and efficiency of information retrieval systems. Through systematic evaluation, various NLP techniques, including tokenization, named entity recognition, semantic parsing, and word embeddings, were found to enhance retrieval performance across diverse datasets and domains. By considering context and user intent, researchers aimed to develop more contextually aware and personalized information retrieval systems. The study emphasized the need for further research to explore hybrid approaches and domain-specific adaptations, ultimately highlighting the transformative potential of NLP in revolutionizing information access and utilization.
 Unique Contribution to Theory, Practice and Policy: Information Foraging theory, Relevance theory and Cognitive Load theory may be used to anchor future studies on Natural Language Processing techniques. The study provided recommendations to enhance information retrieval systems. It suggested integrating advanced NLP techniques such as named entity recognition and sentiment analysis to improve query understanding and document relevance. Additionally, the study recommended adopting word embeddings and semantic parsing techniques for better semantic understanding of user queries and documents. It emphasized the importance of domain-specific adaptations and continuous evaluation of NLP techniques to tailor them to specific application domains and keep pace with evolving user needs and technological advancements.

CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework

Multilingual code retrieval aims to find code snippets relevant to a user's query from a multilingual codebase, which plays a crucial role in software development and expands their application scenarios compared to classical monolingual code retrieval. Despite the performance improvements achieved by previous studies, two crucial problems are overlooked in the multilingual scenario. First, certain programming languages face data scarcity in specific domains, resulting in limited representation capabilities within those domains. Second, different programming languages can be used interchangeably within the same domain, making it challenging for multilingual models to accurately identify the intended programming language of a user's query. To address these issues, we propose the CommONalities and SpecIalties Driven Multilingual CodE Retrieval Framework (CONSIDER), which includes two modules. The first module enhances the representation of various programming languages by modeling pairwise and global commonalities among them. The second module introduces a novel contrastive learning negative sampling algorithm that leverages language confusion to automatically extract specific language features. Through our experiments, we confirm the significant benefits of our model in real-world multilingual code retrieval scenarios in various aspects. Furthermore, an evaluation demonstrates the effectiveness of our proposed CONSIDER framework in monolingual scenarios as well. Our source code is available at https://github.com/smsquirrel/consider.

ORES: Open-Vocabulary Responsible Visual Synthesis

Avoiding synthesizing specific visual concepts is an essential challenge in responsible visual synthesis. However, the visual concept that needs to be avoided for responsible visual synthesis tends to be diverse, depending on the region, context, and usage scenarios. In this work, we formalize a new task, Open-vocabulary Responsible Visual Synthesis (ORES), where the synthesis model is able to avoid forbidden visual concepts while allowing users to input any desired content. To address this problem, we present a Two-stage Intervention (TIN) framework. By introducing 1) rewriting with learnable instruction through a large-scale language model (LLM) and 2) synthesizing with prompt intervention on a diffusion synthesis model, it can effectively synthesize images avoiding any concepts but following the user's query as much as possible. To evaluate on ORES, we provide a publicly available dataset, baseline models, and benchmark. Experimental results demonstrate the effectiveness of our method in reducing risks of image generation. Our work highlights the potential of LLMs in responsible visual synthesis. Our code and dataset is public available in https://github.com/kodenii/ORES.

Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought

With the proliferation of dialogic data across the Internet, the Dialogue Commonsense Multi-choice Question Answering (DC-MCQ) task has emerged as a response to the challenge of comprehending user queries and intentions. Although prevailing methodologies exhibit effectiveness in addressing single-choice questions, they encounter difficulties in handling multi-choice queries due to the heightened intricacy and informational density. In this paper, inspired by the human cognitive process of progressively excluding options, we propose a three-step Reverse Exclusion Graph-of-Thought (ReX-GoT) framework, including Option Exclusion, Error Analysis, and Combine Information. Specifically, our ReX-GoT mimics human reasoning by gradually excluding irrelevant options and learning the reasons for option errors to choose the optimal path of the GoT and ultimately infer the correct answer. By progressively integrating intricate clues, our method effectively reduces the difficulty of multi-choice reasoning and provides a novel solution for DC-MCQ. Extensive experiments on the CICERO and CICERO_v2 datasets validate the significant improvement of our approach on DC-MCQ task. On zero-shot setting, our model outperform the best baseline by 17.67% in terms of F1 score for the multi-choice task. Most strikingly, our GPT3.5-based ReX-GoT framework achieves a remarkable 39.44% increase in F1 score.

SAME: Sample Reconstruction against Model Extraction Attacks

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged, lowering the barriers for users to release or productize their deep learning models. However, previous studies have highlighted potential privacy and security concerns associated with MLaaS, and one primary threat is model extraction attacks. To address this, there are many defense solutions but they suffer from unrealistic assumptions and generalization issues, making them less practical for reliable protection. Driven by these limitations, we introduce a novel defense mechanism, SAME, based on the concept of sample reconstruction. This strategy imposes minimal prerequisites on the defender's capabilities, eliminating the need for auxiliary Out-of-Distribution (OOD) datasets, user query history, white-box model access, and additional intervention during model training. It is compatible with existing active defense methods. Our extensive experiments corroborate the superior efficacy of SAME over state-of-the-art solutions. Our code is available at https://github.com/xythink/SAME.

GEAR-Up: Generative AI and External Knowledge-Based Retrieval: Upgrading Scholarly Article Searches for Systematic Reviews

This paper addresses the time-intensive nature of systematic reviews (SRs) and proposes a solution leveraging advancements in Generative AI (e.g., ChatGPT) and external knowledge augmentation (e.g., Retrieval-Augmented Generation). The proposed system, GEAR-Up, automates query development and translation in SRs, enhancing efficiency by enriching user queries with context from language models and knowledge graphs. Collaborating with librarians, qualitative evaluations demonstrate improved reproducibility and search strategy quality. Access the demo at https://youtu.be/zMdP56GJ9mU.

AI-Based Medical Chatbot for Disease Prediction By IJISRT

This research paper presents the development and implementation of an AI-based medical chatbot for disease prediction. Leveraging machine learning and artificial intelligence technologies, the chatbot utilizes natural language processing (NLP) to understand user queries and provide accurate information, guidance, and assistance for various infectious diseases. Motivated by the global spread of infectious diseases and the need for accessible healthcare support, the paper outlines the objectives, algorithm design, dataset description, and application of the chatbot. The algorithm involves receiving user input, extracting symptoms, classifying diseases, and suggesting prevention measures. The dataset, structured in JSON format, facilitates training and pattern recognition. The chatbot interface, accessible across platforms, offers information on symptoms, prevention measures, hospital bed availability, and medication options. In conclusion, the research highlights the potential of AI-based chatbots in revolutionizing healthcare accessibility and personalized diagnosis, thereby bridging the gap between users and healthcare systems.

Large Language Model for Chatbot

The integration of Artificial Intelligence (AI) and Natural Language Processing (NLP) has led to the development of sophisticated Chatbots capable of mimicking human conversation and providing automated responses. In the context of the mining industry, which operates under a complex framework of Acts, Rules, and Regulations, there is a growing need for a comprehensive and easily accessible information system. This research proposes the implementation of a 24/7 available Chatbot, equipped with the ability to address stakeholder and customer queries regarding various legal aspects, including the Coal Mines Act, 1952, Indian Explosives Act, 1884, Colliery Control Order, 2000, Colliery Control Rules, 2004, The Coal Mines Regulations, 2017, and The Payment of Wages (Mines) Rules, 1956. Furthermore, the Chatbot's scope will encompass land-related laws, such as Community Benefits Agreement (CBA), Land Acquisition (LA), and Resettlement and Rehabilitation (RandR), thereby establishing a robust Management Information System tailored to the specific needs of the mining industry

Joint Representation Learning for Retrieval and Annotation of Genomic Interval Sets.

As available genomic interval data increase in scale, we require fast systems to search them. A common approach is simple string matching to compare a search term to metadata, but this is limited by incomplete or inaccurate annotations. An alternative is to compare data directly through genomic region overlap analysis, but this approach leads to challenges like sparsity, high dimensionality, and computational expense. We require novel methods to quickly and flexibly query large, messy genomic interval databases. Here, we develop a genomic interval search system using representation learning. We train numerical embeddings for a collection of region sets simultaneously with their metadata labels, capturing similarity between region sets and their metadata in a low-dimensional space. Using these learned co-embeddings, we develop a system that solves three related information retrieval tasks using embedding distance computations: retrieving region sets related to a user query string, suggesting new labels for database region sets, and retrieving database region sets similar to a query region set. We evaluate these use cases and show that jointly learned representations of region sets and metadata are a promising approach for fast, flexible, and accurate genomic region information retrieval.

A Study to Know the Impact of AI on Sustainability of Products in the Carbonated Beverages

Carbonated beverage businesses are using artificial intelligence (AI) technology to sustainability in a variety of ways to streamline their processes, boost output, and improve the customer experience. The businesses in the carbonated beverage sector use AI in the following ways, Coca-Cola is enhancing its supply chain administration by utilizing AI. The business has created a platform powered by AI that applies machine learning algorithms to improve its distribution and manufacturing procedures. The platform aids the business in improved demand forecasting, inventory level optimization, cost-effective transportation, voice activated vending machines. PepsiCo: To create novel product formulations, PepsiCo is utilizing AI. The business has developed an AI-powered platform that examines customer preferences and spots market trends. The business can develop new products thanks to this platform. Dr. Pepper Snapple Group: Dr. Pepper Snapple Group is enhancing its marketing initiatives with artificial intelligence. The business has created an AI-driven platform that analyses customer data and enables it to develop more specialized and individualized marketing campaigns. The platform enables the business to deliver more pertinent and efficient marketing messages by assisting in the better understanding of customer preferences and behaviour. Keurig Dr Pepper: Keurig Dr Pepper is using AI to enhance its customer service. The business has created an AI-powered chatbot that can instantly respond to customer inquiries and help. The chatbot uses machine learning algorithms and natural language processing to comprehend customer queries and deliver pertinent and useful responses. Overall, the carbonated beverage industry is using AI technology in a variety of methods. Keywords- carbonated beverage, artificial intelligence (AI), supply chain administration, demand forecasting, inventory optimization, transportation optimization, voice activated vending machines, product formulation, customer preferences, market trends, marketing campaigns, customer service, chatbot, machine learning algorithms, natural language processing.

Empowering personalized pharmacogenomics with generative AI solutions.

This study evaluates an AI assistant developed using OpenAI's GPT-4 for interpreting pharmacogenomic (PGx) testing results, aiming to improve decision-making and knowledge sharing in clinical genetics and to enhance patient care with equitable access. The AI assistant employs retrieval-augmented generation (RAG), which combines retrieval and generative techniques, by harnessing a knowledge base (KB) that comprises data from the Clinical Pharmacogenetics Implementation Consortium (CPIC). It uses context-aware GPT-4 to generate tailored responses to user queries from this KB, further refined through prompt engineering and guardrails. Evaluated against a specialized PGx question catalog, the AI assistant showed high efficacy in addressing user queries. Compared with OpenAI's ChatGPT 3.5, it demonstrated better performance, especially in provider-specific queries requiring specialized data and citations. Key areas for improvement include enhancing accuracy, relevancy, and representative language in responses. The integration of context-aware GPT-4 with RAG significantly enhanced the AI assistant's utility. RAG's ability to incorporate domain-specific CPIC data, including recent literature, proved beneficial. Challenges persist, such as the need for specialized genetic/PGx models to improve accuracy and relevancy and addressing ethical, regulatory, and safety concerns. This study underscores generative AI's potential for transforming healthcare provider support and patient accessibility to complex pharmacogenomic information. While careful implementation of large language models like GPT-4 is necessary, it is clear that they can substantially improve understanding of pharmacogenomic data. With further development, these tools could augment healthcare expertise, provider productivity, and the delivery of equitable, patient-centered healthcare services.

A data model for enabling deep learning practices on discovery services of cyber‐physical systems

AbstractThe W3C Web of Things (WoT) is a leading technology that facilitates dynamic information management in the Internet of Things (IoT). In most IoT scenarios, devices and their associated information change continuously, generating a large amount of data. Hence, to correctly use the information and the data generated by different devices, a new perspective of managing and ensuring data quality is recommended. Applying Data Science techniques to create the data model can help to manage and ensure data quality by creating a common schema that can be reused in future projects, as well as producing recommendations to facilitate Service Discovery. In addition, due to the dynamic devices that change over time or under specific circumstances, the data model created must be sufficiently abstract to add new instances and to support new requirements that devices should incorporate. The use of models helps to raise the abstraction level, adapting it to the continuous changes of devices by defining instances associated with the data model. This paper proposes two data models: one for Cyber‐Physical Systems (CPS) to define device information fetched by a Discovery Service, and another for applying Deep Learning in natural language problems through a Transformer approach. The latter matches user queries in natural language sentences with WoT devices or services. These data models expand the Thing Description model to help find similar CPSs by giving a confidence level to each CPS based on features such as security and the number of times the device was accessed. The results show how the proposed models support the search process of CPSs in syntactic and natural language searches. Furthermore, the four levels of the FAIR principles are validated for the proposed data models, thus ensuring the data's transparency, reproducibility, and reusability.

ANNProof: Building a verifiable and efficient outsourced approximate nearest neighbor search system on blockchain

Data-as-a-service is increasingly prevalent, with outsourced K-approximate nearest neighbors search (K-ANNS) gaining popularity in applications like similar image retrieval and anti-money laundering. However, malicious search service providers and dataset providers in current outsourced query systems cause incorrect user query results. To address this, we propose ANNProof, a novel framework supporting verifiable outsourced K-ANNS on the blockchain. ANNProof utilizes two innovative authenticated data structures (ADS), the Merkle HNSW node tree, and the Merkle vector identifier tree, for efficient K-ANNS query verification. Additionally, we employ the Merkle sharding tree as an ADS optimization technique, reducing the overhead of delivering verifiable queries. We implement the ADS construction protocol based on blockchain smart contracts to ensure tamper-evident datasets and enhance execution efficiency via a contract state consistency checking scheme. Extensive evaluations show that ANNProof reduces VO generation time, result verification time, and VO size by 160, 120, and 28×, respectively, compared to the state-of-the-art systems. Moreover, ADS construction using ANNProof takes at most 2% of the index construction time, resulting in a negligible overhead for implementing verifiable queries. Meanwhile, the sharding optimization accelerates ADS updates by 53×.

Transformer-Based Classification of User Queries for Medical Consultancy

Transformer-Based Classification of User Queries for Medical Consultancy