Triplétoile: Extraction of knowledge from microblogging text

This paper investigates the impact of knowledge extraction methods on the effectiveness of RAG (Retrieval-Augmented Generation) systems that utilize knowledge graphs. It highlights that the quality of the knowledge graph, which is formed using various knowledge extraction methods, is crucial for overcoming limitations of large language models (LLMs), such as “hallucinations”. The paper analyzes the architectures of LightRAG and GraphRAG, emphasizing that the selection of an optimal knowledge extraction strategy depends on specific tasks and the subject area. LLMs have advanced significantly, but they have limitations, including generating factually incorrect information (“hallucinations”) and possessing “outdated knowledge”. RAG systems were proposed to address these issues by combining LLMs with external knowledge bases. This approach reduces hallucinations, ensures factual accuracy, solves the problem of outdated knowledge, and increases transparency. Knowledge graphs are powerful tools for structuring information, consisting of entities (nodes) and relations (edges). They enhance RAG systems by enabling more precise and contextually grounded retrieval compared to keyword-based searches. The quality of a knowledge graph depends on the knowledge extraction methods used, which include named entity recognition (NER), relation extraction (RE), entity linking (EL), and event extraction. Different methods, such as rule-based, classical machine learning, and deep learning approaches, have varying trade-offs in terms of accuracy, completeness, and scalability. Entity linking and knowledge graph completion are also crucial for accuracy and richness. LightRAG and GraphRAG are two main graph-based RAG systems. LightRAG uses the knowledge graph as a quick reference, requiring high precision in knowledge extraction to avoid noise degradation. GraphRAG uses the knowledge graph as a domain model, where completeness of extracted knowledge is more critical, though systematic errors are still harmful. Both systems rely on LLMs for knowledge extraction, which makes them dependent on the LLM’s quality and the size of document fragments processed. The theoretical analysis confirms that the effectiveness of RAG systems is critically dependent on knowledge extraction methods. The quality, completeness, and accuracy of the knowledge graph directly influence the RAG system’s ability to provide relevant, accurate, and truthful answers. Different RAG system architectures like LightRAG and GraphRAG have distinct requirements for knowledge graph characteristics, prioritizing either accuracy or completeness in knowledge extraction.

Neural symbolic reasoning with knowledge graphs: Knowledge extraction, relational reasoning, and inconsistency checking

Extracting and organizing knowledge from the agricultural crop disease research literature are challenging tasks because of the heterogeneous terminologies, complicated symptom descriptions, and unstructured nature of scientific documents. In this study, we developed a multi-stage natural language processing (NLP) pipeline to automate knowledge extraction, organization, and integration from the agricultural research literature into a domain-consistent crop disease knowledge graph. The model combines transformer-based sentence embeddings with variational deep clustering to extract topics, which are further refined via facet-aware relevance scoring for sentence selection to be included in the summary. Lexicon-guided named entity recognition helps in the precise identification and normalization of terms for crops, diseases, symptoms, etc. Relation extraction based on a combination of lexical, semantic, and contextual features leads to the meaningful generation of triplets for the knowledge graph. The experimental results show that the method yielded consistently good results at each stage of the knowledge extraction process. Among the combinations of embedding and deep clustering methods, SciBERT + VaDE achieved the best clustering results. The extraction of representative sentences for disease symptoms, control/treatment, and prevention obtained high F1-scores of around 0.8. The resulting knowledge graph has high node coverage and high relation completeness, as well as high precision and recall in triplet generation. The multi-stage NLP pipeline effectively converts unstructured agricultural research texts into a coherent and semantically rich knowledge graph, providing a basis for further research in crop disease analysis, knowledge retrieval, and data-driven decision support in agricultural informatics.

BackgroundThe COVID-19 pandemic has created a global health crisis that is affecting economies and societies worldwide. During times of uncertainty and unexpected change, people have turned to social media platforms as communication tools and primary information sources. Platforms such as Twitter and Sina Weibo have allowed communities to share discussion and emotional support; they also play important roles for individuals, governments, and organizations in exchanging information and expressing opinions. However, research that studies the main concerns expressed by social media users during the pandemic is limited.ObjectiveThe aim of this study was to examine the main concerns raised and discussed by citizens on Sina Weibo, the largest social media platform in China, during the COVID-19 pandemic.MethodsWe used a web crawler tool and a set of predefined search terms (New Coronavirus Pneumonia, New Coronavirus, and COVID-19) to investigate concerns raised by Sina Weibo users. Textual information and metadata (number of likes, comments, retweets, publishing time, and publishing location) of microblog posts published between December 1, 2019, and July 32, 2020, were collected. After segmenting the words of the collected text, we used a topic modeling technique, latent Dirichlet allocation (LDA), to identify the most common topics posted by users. We analyzed the emotional tendencies of the topics, calculated the proportional distribution of the topics, performed user behavior analysis on the topics using data collected from the number of likes, comments, and retweets, and studied the changes in user concerns and differences in participation between citizens living in different regions of mainland China.ResultsBased on the 203,191 eligible microblog posts collected, we identified 17 topics and grouped them into 8 themes. These topics were pandemic statistics, domestic epidemic, epidemics in other countries worldwide, COVID-19 treatments, medical resources, economic shock, quarantine and investigation, patients’ outcry for help, work and production resumption, psychological influence, joint prevention and control, material donation, epidemics in neighboring countries, vaccine development, fueling and saluting antiepidemic action, detection, and study resumption. The mean sentiment was positive for 11 topics and negative for 6 topics. The topic with the highest mean of retweets was domestic epidemic, while the topic with the highest mean of likes was quarantine and investigation.ConclusionsConcerns expressed by social media users are highly correlated with the evolution of the global pandemic. During the COVID-19 pandemic, social media has provided a platform for Chinese government departments and organizations to better understand public concerns and demands. Similarly, social media has provided channels to disseminate information about epidemic prevention and has influenced public attitudes and behaviors. Government departments, especially those related to health, can create appropriate policies in a timely manner through monitoring social media platforms to guide public opinion and behavior during epidemics.

Petroleum industry is currently undergoing a critical period of “digital transformation and intelligent development.” As standards are an important component of national economic and social development, their digital transformation is an inevitable trend. To address the problems of the inability to systematically and efficiently utilize standard knowledge in the petroleum industry, as well as the barriers to knowledge transmission between machines and standard documents, this article takes petroleum industry standard documents as the data source. This article summarizes the model construction strategy, information extraction scheme, knowledge fusion and storage. Finally, the application of the standard document knowledge graph is discussed. To establish the foundation for the direct application of key indicators and other knowledge in standards by machines and provide reference ideas for other fields to conduct digital research on standards.

At present, we are witnessing the transition to a new level of economic development. And the most interesting thing is that both state-owned enterprises and private companies are coping with the challenges and tasks that the modern world puts before them. Modern challenges and challenges lead to significant changes in the activities of each economic entity. And any changes are difficult. Even more difficult are the changes associated with digital transformation; there are many more nuances, uncertainties and solutions. Digital transformation is an essential condition for changes and the formation of the digital economy, the formation of which takes place both within a single country and at the global level as a whole. The purpose of the study is to define the concept of digital transformation; to identify the differences between the concept of digital transformation and automation and digitalization; to determine the key elements of the digital transformation strategy and the state of digital transformation of state authorities in Russia. In this regard, the article analyzes the prerequisites for the global digital transformation; analyzes the national experience and the significance of the digital transformation of state authorities; justifies the need to identify the key elements of the strategy in order to intensify the digital development of any economic agent and identify omissions in the inaccurate definition of the elements of the digital strategy. Results of the study: 1. The analysis of the concepts of automation, digitalization and digital transformation is carried out. 2. The role of digital transformation for business and the state is shown. 3. The key elements of the digital transformation strategy are proposed. 4. The directions for implementing the digital transformation of the business and the environment are identified. The methodological basis of the research is the scientific works of Russian and foreign scientists in the field of digital economy, the results of various applied studies on the formation of a new way of economy. Based on the analysis of domestic and foreign literature, digital transformation appears as a strategic direction for the development of any business and the environment as a whole.

In the context of digital transformation in enterprises, how financial social media affects investors' perceptions is a core issue. This study quantitatively examines investors' emotions on social media platforms from the perspective of financial social media. The study explores whether investors are influenced by financial social media in their investment decisions through the use of interview methods, and quantifies the influencing factors of investment decisions to explore the degree of influence of financial social media on investors. According to research findings, digital transformation of companies can greatly improve investor sentiment by increasing performance expectations and media communication. According to this study, financial social media has become an important window for investors to understand. In order to achieve a positive interaction between digital transformation and investor sentiment, it is necessary to rely on the quality of digital communication and ensure transparency of information. In the background of the change in the digitization of the firm, it is a core problem how financial social media affects investors' feelings. Based on the viewpoint of financial social media, this study quantitatively examines investors' emotions on social media platforms. According to research, the conversion of digitization of the company can greatly improve the investor's emotion by raising performance expectation and media broadcasting. According to the study, financial social media has become an important window for investors to know.

In the recent decade, knowledge graph has been a key technique under quick development in artificial intelligence. Due to its great potential for tackling big data and solving complex scientific questions in the geosciences, it has attracted the attention of both computer scientists and geoscientists. In this paper, we review concepts and technologies relevant to the knowledge graph, the workflow of geoscience knowledge graph construction, and state-of-the-art examples from several geoscience disciplines. There are two general strategies for constructing geoscience knowledge graphs: top-down and bottom-up. The detailed technologies include geoscience domain knowledge modeling, data collection, knowledge extraction, knowledge cleaning and fusion, knowledge storage, and knowledge service and discovery. A few recent studies have shown that knowledge graph is a useful tool for improving our understanding of the evolution of the Earth and can assist in data-intensive geoscience studies. At the end of the paper, we discuss the best practices from the studies reviewed and propose research topics for future work. Both knowledge and rules in existing human-curated databases and text mining from the literature should be leveraged in constructing geoscience knowledge graphs. Moreover, development of a higher level schema for existing ontology models and a comparable training corpus should be considered.

Tailoring personalized treatments demands the analysis of a patient’s characteristics, which may be scattered over a wide variety of sources. These features include family history, life habits, comorbidities, and potential treatment side effects. Moreover, the analysis of the services visited the most by a patient before a new diagnosis, as well as the type of requested tests, may uncover patterns that contribute to earlier disease detection and treatment effectiveness. Built on knowledge-driven ecosystems, we devise DE4LungCancer, a health data ecosystem of data sources for lung cancer. In this data ecosystem, knowledge extracted from heterogeneous sources, e.g., clinical records, scientific publications, and pharmacological data, is integrated into knowledge graphs. Ontologies describe the meaning of the combined data, and mapping rules enable the declarative definition of the transformation and integration processes. DE4LungCancer is assessed regarding the methods followed for data quality assessment and curation. Lastly, the role of controlled vocabularies and ontologies in health data management is discussed, as well as their impact on transparent knowledge extraction and analytics. This paper presents the lessons learned in the DE4LungCancer development. It demonstrates the transparency level supported by the proposed knowledge-driven ecosystem, in the context of the lung cancer pilots of the EU H2020-funded project BigMedilytic, the ERA PerMed funded project P4-LUCAT, and the EU H2020 projects CLARIFY and iASiS.

Introduction: Informal caregivers who offer unpaid assistance to family and friends in need navigate complex challenges during their caregiving journey. Seeking support and guidance, many caregivers turn to social media (SM) platforms, marking a crucial intersection between technology transfer, digital transformation, and sustainability in caregiving. Methods: Twenty-four caregivers from diverse regions of Saudi Arabia were interviewed, semi-structured interviews, to gauge the extent to which they utilized SM in caregiving tasks. Results: Our analysis revealed broad patterns of SM utilization among caregivers, characterized by four main themes. Most participants actively used SM platforms to seek medical information, communicate with physicians, and participate in support groups. Educational background influenced adoption patterns, with varying levels of engagement across educational attainment. While the majority leveraged multiple platforms, such as WhatsApp, Twitter, and Instagram, for medical information access and healthcare providers (HCPs) communication, some participants expressed reservations and hesitancy about SM use in caregiving. Notably, participants utilized these platforms for resource management and accessing educational materials about caregiving techniques, demonstrating the multifaceted role of SM in supporting informal caregivers. Conclusion: Our findings revealed widespread SM use among informal caregivers, depicting the adoption of new technologies and a shift toward secure, high-quality care. The caregivers leveraged SM for medical information, consultations, and support group participation. Nevertheless, skepticism exists with some caregivers not trusting SM as an enabler of caregiving duties. Future research may focus on enhancing caregivers’ experiences, facilitating their tasks, and improving their loved one’s health through wider technological deployment and digital health transformation activities.

Many scientific papers, articles, and books related to digitization, digitalization, and digital transformation have been published, and many issues are defined, researched, and discussed for two decades already worldwide, yet with timid application in real life. However, the digital transformation process in many countries has been significantly accelerated by the Covid-19 difficult situations due to social distance restrictions, and especially the lockdowns imposed by governments. The paper summarizes the roadmap to digital transformation in 193 countries according to EGDI (United Nations E-Government Development Index), the EU’s main areas for multi-projects, and Romania’s e-Government and e-Business current situation. There are also presented a number of examples of successful e-Government and e-Business projects in Romania.

with the increase in internet use, a large amount of online business news text articles are posting on web portals, social media platforms, and other information-sharing platforms. For any business news platform, it is very crucial for organizing such business news articles for their subscribers, readers, traders, and investors. These business articles are on focused and specific themes like new hiring, funding, IPO, NFO, merger, and acquisitions. These themes may overlap with each other because of similar domain jargon and vocabulary. Efficient segregation of these business articles makes it easier to manage and handle. The clustering algorithm can be useful for grouping and segregating business articles efficiently. These groups and clusters are highly similar within clusters compared to other clusters. Clustering business articles is applicable in web mining, search engine, business news summarization, and information retrieval. In this paper, we are clustering the business news articles scraped from various news portals using various feature engineerings such as BoW, TF-IDF, Part of Speech (PoS) tags, Named Entity Recognition (NER) tags, and Word Embedding such as Word2Vec (CBOW and Skip-gram) and Doc2Vec (PV-DBOW and PV-DM) and grouped the business news articles using Multi-objective Particle Swarm optimization (MOPSO) clustering approach. We have compared the results with available cluster analysis techniques such as K-means, GMM, hierarchical, spectral, and HMM clustering techniques.

PurposeThis article aims to elaborate on the current relevant policies, research literature and technical applications of administrative intelligent decision-making in major countries in the world, to summarize the current focus areas of international competition in administrative intelligent decision-making and to provide references and insights for other countries.Design/methodology/approachThe knowledge graph tool CiteSpace was used to conduct a quantitative analysis of the field of administrative intelligent decision-making, using the two dimensions of research literature and technology patents to analyze the basic status and evolution process of artificial intelligence applied to administrative decision-making.FindingsOver the past 30 years, theoretical research on administrative intelligent decision-making has primarily centered on countries like the United States of America, China and Japan. The main themes include leveraging artificial intelligence (AI) technology to enable digital government transformation, enhance administrative efficiency and promote public value through service-oriented initiatives. Countries like South Korea, China and the United States of America have demonstrated significant advantages in technology development and patent applications, focusing on e-government systems, intelligent government auditing, addressing policy mismatches between supply and demand and integrating online and offline administrative services. The international competitive landscape in this field is shaped by three key factors: foundational theories, technological advancements and practical scenario applications.Originality/valueDespite the rapid advancements in AI technology and the acceleration of enterprise digital transformation, discussions on the intelligent transformation of administrative decision-making leveraging next-generation information technology remain limited. This study summarizes the development trajectory of administrative intelligent decision-making in major countries worldwide, analyzes the international competitive landscape of its theoretical and application research and highlights key focus areas. These findings offer valuable insights for advancing the construction of administrative intelligent decision-making systems in other nations.

Extracting information from unstructured and semi-structured geoscience literature is a crucial step in conducting geological research. The traditional machine learning extraction paradigm requires a substantial amount of high-quality manually annotated data for model training, which is time-consuming, labor-intensive, and not easily transferable to new fields. Recently, large language models (LLMs) (e.g., ChatGPT, GPT-4, and LLaMA), have shown great performance in various natural language processing (NLP) tasks, such as question answering, machine translation, and text generation. A substantial body of work has demonstrated that LLMs possess strong in-context learning (ICL) and even zero-shot learning capabilities to solve downstream tasks without specifically designed supervised fine-tuning. In this paper, we propose utilizing LLMs for geoscience literature information extraction. Specifically, we design a hierarchical PDF parsing pipeline and an automated knowledge extraction process, which can significantly reduce the need for manual data annotation, assisting geoscientists in literature data mining. For the hierarchical PDF parsing pipeline, firstly, a document layout detection model fine-tuned on geoscience literature is employed for layout detection, obtaining layout detection information for the document. Secondly, based on the document layout information, an optical character content parsing model is used for content parsing, obtaining the text structure and plain text corresponding to the content. Finally, the text structure and plain text are combined and reconstructed to ultimately obtain the parsed structured data. For the automated knowledge extraction process, firstly, the parsed long text is segmented into paragraphs to adapt to the input length limit of LLMs. Subsequently, a few-shot prompting method is employed for structured knowledge extraction, encompassing two tasks: attribute value extraction and triplet extraction. In attribute value extraction, prompts are generated automatically by the LLMs based on the subdomain and attribute names, facilitating the location and extraction of values related to subdomain attribute names in the text. For triplet extraction, the LLMs employ a procedural approach to entity extraction, entity type extraction, and relation extraction, following the knowledge graph structure pattern. Finally, the extracted structured knowledge is stored in the form of knowledge graphs, facilitating further analysis and integration of various types of knowledge from the literature. Our proposed approach turns out to be simple, flexible, and highly effective in geoscience literature information extraction. Demonstrations of information extraction in subdomains such as radiolarian fossils and fluvial facies have yielded satisfactory results. The extraction efficiency has significantly improved, and feedback from domain experts indicates a relatively high level of accuracy in the extraction process. The extracted results can be used to construct a foundational knowledge graph for geoscience literature, supporting the comprehensive construction and efficient application of a geoscience knowledge graph.

Several scholarly knowledge graphs have been proposed to model and analyze the academic landscape. However, although the number of data sets has increased remarkably in recent years, these knowledge graphs do not primarily focus on data sets but rather on associated entities such as publications. Moreover, publicly available data set knowledge graphs do not systematically contain links to the publications in which the data sets are mentioned. In this paper, we present an approach for constructing an RDF knowledge graph that fulfills these mentioned criteria. Our data set knowledge graph, DSKG, is publicly available at http://dskg.org and contains metadata of data sets for all scientific disciplines. To ensure high data quality of the DSKG, we first identify suitable raw data set collections for creating the DSKG. We then establish links between the data sets and publications modeled in the Microsoft Academic Knowledge Graph that mention these data sets. As the author names of data sets can be ambiguous, we develop and evaluate a method for author name disambiguation and enrich the knowledge graph with links to ORCID. Overall, our knowledge graph contains more than 2,000 data sets with associated properties, as well as 814,000 links to 635,000 scientific publications. It can be used for a variety of scenarios, facilitating advanced data set search systems and new ways of measuring and awarding the provisioning of data sets.