Knowledge-intensive Domains Research Articles

A link prediction method for Chinese financial event knowledge graph based on graph attention networks and convolutional neural networks

Finance is a knowledge-intensive domain in nature, with its data containing a significant amount of interconnected information. Constructing a financial knowledge graph is an important application for transforming financial text/web content into machine-readable data. However, the complexity of Chinese financial knowledge and the dynamic and evolving nature of Chinese financial data often lead to incomplete knowledge graphs. To address this challenge, we propose a novel link prediction method for Chinese financial event knowledge graph based on Graph Attention Networks and Convolutional Neural Networks. Our method begins with the construction of the foundational Chinese financial event knowledge graph using a relational triple extraction module integrated with a large language model framework, along with a Prompting with Iterative Verification (PiVe) module for validation. To enhance the completeness of the knowledge graph, we introduce an encoder-decoder framework, where a graph attention network with joint embeddings of financial event entities and relations acts as the encoder, while a Convolutional Knowledge Base embedding model (ConvKB) serves as the decoder. This framework effectively aggregates crucial neighbor information and captures global relationships among entity and relation embeddings. Extensive comparative experiments demonstrate the utility and accuracy of this method, ultimately enabling the effective completion of Chinese financial event knowledge graphs.

Creational and conversational AI affordances: How the new breed of chatbots is revolutionizing knowledge industries

The new generative AI (GenAI) paradigm offers unprecedented opportunities for users to tap into. AI capabilities are increasingly helpful in creative and knowledge-intensive domains that have long been considered a territory of human expertise. The new breed of chatbots is based on large language models (LLMs), and they have overcome many constraints that plague the everyday use of previous AI technologies. This article employs the theory of affordances to understand how ChatGPT facilitates (i.e., affords) and constrains (i.e., disaffords) the usefulness of a new breed of chatbots. We further divide two distinct yet interrelated dimensions of new AI affordances: creational and conversational. Via 29 interviews with professionals using ChatGPT in various creative and knowledge-intensive sectors, we identify three creational affordances (content creation and enhancement, knowledge acquisition and creativity augmentation, and task automation) and three conversational affordances (contextual sensitivity, interactive accessibility, and human-AI workflow synergy). Creational affordances refer to the system’s ability to produce novel outputs and automate routine work, whereas conversational affordances encompass the variety of interaction possibilities with an AI system. Both affordances also involve disaffordances that limit the usefulness of the new types of AI systems. Furthermore, we introduce an integrated framework that shows how creational and conversational affordances reinforce each other via meta-affordances of accessibility, accumulation, and adaptability. We illustrate our findings with practical examples and offer guidelines for using these emerging capabilities in company settings.

Research on the Aided Diagnosis Method of Diseases Based on Domain Semantic Knowledge Bases

The health care domain is a knowledge-intensive domain. The quality of clinical diagnosis relies mainly on the medical knowledge and experience held by doctors. However, the ability of a single doctor is very limited, so the quality of clinical diagnosis is currently not high. In this paper, an aided diagnosis method based on domain semantic knowledge bases is proposed. Firstly, a domain semantic knowledge base is established by extracting and refining the knowledge of the medicine subject matter domain from the Freebase RDF dumps. Then, based on the semantic knowledge base, the algorithms for calculating the weights of the symptoms in the knowledge base, the relative weights of the diseases related to the input symptom set from a patient, and the related symptom set related to the input symptom set from the patient are proposed. Finally, the clinical medical record data of several common diseases are selected to make an evaluation on the proposed method. For each medical record, the symptom information is extracted from the chief complaint as the patient’s input symptom set. Based on the input symptom set, the method of this paper is used to obtain the list of related diseases and the ranking of disease relative weights. From the disease relevance rankings, the Top 1 (first diagnosis) and Top-3 (first 3 diagnoses) are compared with the doctor’s diagnoses in the medical records. Among them, ovarian cyst has the highest Top-1 and Top-3 hit rates of 67.3% and 89.1%, respectively. Followed by acute upper respiratory tract infection, Top-1 and Top-3 hit rates are 56.6% and 85.2%, respectively. The average Top-1 and Top-3 hit rates are 47.9% and 79.7%, respectively. Compared with the relevant methods, the method of this paper is better. The evaluation results show that based on the domain semantic knowledge base and the aided diagnosis method of diseases constructed in this paper, it is possible to provide aided diagnosis services of a large number of common diseases for general practitioners (especially inexperienced doctors) at the grass-roots level as well as self-diagnosis services of diseases for patients.

DEVELOPMENT OF A QUESTION ANSWERING CHATBOT FOR BLOCKCHAIN DOMAIN

Large Language Models (LLMs), such as ChatGPT, have transformed the field of natural language processing with their capacity for language comprehension and generation of human-like, fluent responses for many downstream tasks. Despite their impressive capabilities, they often fall short in domain-specific and knowledge-intensive domains due to a lack of access to relevant data. Moreover, most state-of-art LLMs lack transparency as they are often accessible only through APIs. Furthermore, their application in critical real-world scenarios is hindered by their proclivity to produce hallucinated information and inability to leverage external knowledge sources. To address these limitations, we propose an innovative system that enhances LLMs by integrating them with an external knowledge management module. The system allows LLMs to utilize data stored in vector databases, providing them with relevant information for their responses. Additionally, it enables them to retrieve information from the Internet, further broadening their knowledge base. The research approach circumvents the need to retrain LLMs, which can be a resource-intensive process. Instead, it focuses on making more efficient use of existing models. Preliminary results indicate that the system holds promise for improving the performance of LLMs in domain-specific and knowledge-intensive tasks. By equipping LLMs with real-time access to external data, it is possible to harness their language generation capabilities more effectively, without the need to continually strive for larger models.

MPTP: Motion-planning-aware task planning for navigation in belief space

We present an integrated Task-Motion Planning (TMP) framework for navigation in large-scale environments. Of late, TMP for manipulation has attracted significant interest resulting in a proliferation of different approaches. In contrast, TMP for navigation has received considerably less attention. Autonomous robots operating in real-world complex scenarios require planning in the discrete (task) space and the continuous (motion) space. In knowledge-intensive domains, on the one hand, a robot has to reason at the highest-level, for example, the objects to procure, the regions to navigate to in order to acquire them; on the other hand, the feasibility of the respective navigation tasks have to be checked at the execution level. This presents a need for motion-planning-aware task planners. In this paper, we discuss a probabilistically complete approach that leverages this task-motion interaction for navigating in large knowledge-intensive domains, returning a plan that is optimal at the task-level. The framework is intended for motion planning under motion and sensing uncertainty, which is formally known as belief space planning. The underlying methodology is validated in simulation, in an office environment and its scalability is tested in the larger Willow Garage world. A reasonable comparison with a work that is closest to our approach is also provided. We also demonstrate the adaptability of our approach by considering a building floor navigation domain. Finally, we also discuss the limitations of our approach and put forward suggestions for improvements and future work.

Defining the big social data paradigm through a systematic literature review approach

PurposeThis study aims to investigate the Big Social Data (BSD) paradigm, which still lacks a clear and shared definition, and causes a lack of clarity and understanding about its beneficial opportunities for practitioners. In the knowledge management (KM) domain, a clear characterization of the BSD paradigm can lead to more effective and efficient KM strategies, processes and systems that leverage a huge amount of structured and unstructured data sources.Design/methodology/approachThe study adopts a systematic literature review (SLR) methodology based on a mixed analysis approach (unsupervised machine learning and human-based) applied to 199 research articles on BSD topics extracted from Scopus and Web of Science. In particular, machine learning processing has been implemented by using topic extraction and hierarchical clustering techniques.FindingsThe paper provides a threefold contribution: a conceptualization and a consensual definition of the BSD paradigm through the identification of four key conceptual pillars (i.e. sources, properties, technology and value exploitation); a characterization of the taxonomy of BSD data type that extends previous works on this topic; a research agenda for future research studies on BSD and its applications along with a KM perspective.Research limitations/implicationsThe main limits of the research rely on the list of articles considered for the literature review that could be enlarged by considering further sources (in addition to Scopus and Web of Science) and/or further languages (in addition to English) and/or further years (the review considers papers published until 2018). Research implications concern the development of a research agenda organized along with five thematic issues, which can feed future research to deepen the paradigm of BSD and explore linkages with the KM field.Practical implicationsPractical implications concern the usage of the proposed definition of BSD to purposefully design applications and services based on BSD in knowledge-intensive domains to generate value for citizens, individuals, companies and territories.Originality/valueThe original contribution concerns the definition of the big data social paradigm built through an SLR the combines machine learning processing and human-based processing. Moreover, the research agenda deriving from the study contributes to investigate the BSD paradigm in the wider domain of KM.

A Large Scale, Knowledge Intensive Domain Development Methodology

Since time immemorial, organization and visualization has emerged as the pre-eminent natural combination through which abstract concepts in a domain can be understood, imbibed and communicated. In the present era of big data and information explosion, domains are becoming increasingly intricate and facetized, often leaving traditional approaches of know­ledge organization functionally inefficient in dynamically depicting intellectual landscapes. The paper attempts to present, ab initio, a step-by-step conceptual domain development methodology using know­ledge graphs, rooted in the rudiments of interdisciplinary know­ledge organization and know­ledge cartography. It briefly highlights the implementation of the proposed methodology on business domain data, and considers its research ramifications, originality and limitations from multiple perspectives. The paper concludes by summarizing observations on the entire work and particularizing future lines of research.

Boosting Answer Set Optimization with Weighted Comparator Networks

AbstractAnswer set programming (ASP) is a paradigm for modeling knowledge-intensive domains and solving challenging reasoning problems. In ASP solving, a typical strategy is to preprocess problem instances by rewriting complex rules into simpler ones. Normalization is a rewriting process that removes extended rule types altogether in favor of normal rules. Recently, such techniques led to optimization rewriting in ASP, where the goal is to boost answer set optimization by refactoring the optimization criteria of interest. In this paper, we present a novel, general, and effective technique for optimization rewriting based on comparator networks which are specific kinds of circuits for reordering the elements of vectors. The idea is to connect an ASP encoding of a comparator network to the literals being optimized and to redistribute the weights of these literals over the structure of the network. The encoding captures information about the weight of an answer set in auxiliary atoms in a structured way that is proven to yield exponential improvements during branch-and-bound optimization on an infinite family of example programs. The used comparator network can be tuned freely, for example, to find the best size for a given benchmark class. Experiments show accelerated optimization performance on several benchmark problems.

Co-creation in the Design of Technology Enhanced Learning: Teachers’ Beliefs versus Practices

The 4Cs framework, concerning self-regulated professional learning in knowledge intensive domains, is the lens through which participatory practices in learning design are investigated in this paper. The framework identifies four types of participatory behaviours: Consuming, Creating, Connecting and Contributing. A survey involving 117 Italian practicing teachers reveals that they regard all the 4Cs as important, but self-reported behaviours do not align with such beliefs. This misalignment is most significant for Connecting and Contributing behaviours (herein called altruistic behaviours). As for Consuming and Creating (individualistic behaviours), the former is rather scant while the latter is the most practiced, despite a wealth of research addressing the need to make Learning Designs reusable. Besides, the majority of the interviewees do not know the most well-known learning design tools produced by academic research. These data reveal limited impact of learning design research and indicate the way ahead for promoting teachers’ participatory practices.

An Integrative View of Knowledge Processes and a Learning Culture for Ambidexterity: Toward Improved Organizational Performance in the Banking Sector

Banks are the backbone of the financial sector and catalysts in the economic development of any country. Current changes in their global business ecosystem make knowledge of about the fund-supplying and fund-demanding parties of the society a key resource for the fulfillment of banks' investment and saving functions. This paper addresses the relationship between the performance and a learning culture that is supported by knowledge processes within the organization. Given the relevance of this subject for organizations from most knowledge-intensive domains, this research has focused on the Spanish banking sector. Using a structural equation model, feedback received from 215 employees from 142 individual branches from a major banking institution in Spain is studied. The results of the data analysis show that in addition to maximizing on what is already known about the customer base, employees' learning about the potential new stakeholders and also about the internal strategies, tools, and techniques is directly related to the bank's performance, which, in turn, influences the economic recovery and socio-economic development. Results support that an active pursuit of learning within the context of the organization is required for banks to remain competitive in the dynamic, global business ecosystem, where international, national, and local banking sectors operate.

Applying knowledge bases to make factories smarter

Abstract Knowledge Bases (KBs) enable engineers to capture knowledge in a formalized way. This formalization allows us to combine knowledge, thus creating the basis for smart factories while also supporting product and production system design. Building comprehensive and reusable KBs is still a challenge, though, especially for knowledge-intensive domains like engineering and production. To cope with the sheer amount of knowledge, engineers should reuse existing KBs. This paper presents a comprehensive overview of domain-specific KBs for production and engineering, as well as generic top-level ontologies. The application of such top-level ontologies offers new insights by integrating knowledge from various domains, stakeholders, and companies. To bridge the gap between top-level ontologies and existing domain KBs, we introduce an Intermediate Engineering Ontology (IEO).

A feature-based approach towards integration and automation of CAD/CAPP/CAM for EDM electrodes

Electrical discharge machining (EDM) is widely used in mold manufacturing to form the intricate geometric features which are difficult to be produced by the conventional machining process. Owing to the use of a large number of electrodes, the cost and time consumption for electrode design and NC programming has become a bottleneck in boosting productivity of mold enterprises. Although computer-aided design (CAD)/computer-aided manufacturing (CAM) systems are widely used, because of the complex shapes and diversity of electrodes, manual operations are commonly employed to generate process plans and tool paths for electrode manufacturing, which is cumbersome and error-prone. In order to realize the intelligent manufacturing of electrodes in such a knowledge-intensive domain, this paper presents a feature-based integration approach of CAD/computer-aided process planning (CAPP)/CAM. A hierarchical taxonomy of electrode features is introduced and a hybrid feature recognition method is proposed to build multi-level feature tree. Then, feature knowledge and domain know-how based process planning and optimization are achieved followed by automatic tool path generation which aim to machining the electrode precisely and economically. In the framework of system integration, a structured product model is established to capture and encapsulate geometric entities, machining features, technical information, process plans, and measurement data of machining error to realize seamless flow of information among CAD/CAPP/CAM systems. The effectiveness and efficiency of the proposed approach are demonstrated by case studies and industry implementation.

To guide or to follow? Teaching visual problem solving at the workplace

Visual problem solving is essential to highly visual and knowledge-intensive professional domains such as clinical pathology, which trainees learn by participating in relevant tasks at the workplace (apprenticeship). Proper guidance of the visual problem solving of apprentices by the master is necessary. Interaction and adaptation to the expertise level of the learner are identified as key ingredients of this guidance. This study focuses on the effect of increased participation of the learner in the task on the interaction and adaptation of the guidance by masters. Thirteen unique dyads consisting of a clinical pathologist (master) and a resident (apprentice) discussed and diagnosed six microscope images. Their dialogues were analysed on their content. The dyads were divided in two groups according to the experience of the apprentice. For each dyad, master and apprentice both operated the microscope for half of the cases. Interaction was operationalised as the equal contribution of both master and apprentice to the dialogue. Adaptation was operationalised as the extent to which the content of the dialogues was adapted to the apprentice’s level. The main hypothesis stated that the interaction and adaptation increase when apprentices operate the microscope. Most results confirmed this hypothesis: apprentices contributed more content when participating more and the content of these dialogues better reflected expertise differences of apprentices. Based on these results, it is argued that, for learning visual problem solving in a visual and knowledge-intensive domain, it is not only important to externalise master performance, but also that of the apprentice.

The INNOVance Lexicon: Organisation of terms and concepts about construction products

The construction sector is also a knowledge-intensive domain, in which effective and unambiguous communication and knowledge sharing are, at the same time, both essential yet difficult to accomplish. This is primarily due to the several professionals interacting and facing situations involving diverse resources, processes and activities. Each of them brings a different background and perspective, often generating poorly integrated information. Knowledge Organization Systems (KOSs) are crucial for ensuring completeness, consistency and quality of information. Despite the international trend to encourage the development and use of controlled vocabularies, especially classification systems, until recently in Italy the national coordination policy has not been effective enough. This article describes the first national attempt made, the INNOVance Lexicon that collects and organises knowledge about construction products. It combines taxonomic, terminological and semantic aspects of knowledge and it is a reference language to support information exchange and sharing in collaborative context.

To Think Like an Economist A Challenge for Antitrust Lawyers

My paper points to the structural problems in the area of antitrust lawyers’ education and the necessity to recognize economics as a fundamental domain (and not as auxiliary science) in the application of competition law. Independent specialized antitrust courts should be established, and economic education should be mandatory for judges. Economics is a knowledge-intensive domain, and the acquisition of economic knowledge requires special advanced studies. It is not sufficient for lawyers to occasionally familiarize themselves with economic reports and papers. That is not serious. The appropriate response is to integrate economics in the studies of competition law and to establish independent specialized antitrust courts, which would be able to routinely study and to critically and rationally evaluate the antitrust economic and legal questions. Parallelly, economists should be trained in law and support the teams of lawyers of the regulatory authorities. Economists can help courts devise, refine, and reform economic tests.

Self-regulated learning behaviour in the finance industry

Purpose– This paper aims to explore the role of self-regulatory behaviours in predicting workplace learning. As work practices in knowledge-intensive domains become more complex, individual workers must take greater responsibility for their ongoing learning and development.Design/methodology/approach– The study was conducted with knowledge workers from the finance industry. In all, 170 participants across a range of work roles completed a questionnaire consisting of three scales derived from validated instruments (measuring learning opportunities, self-regulated learning [SRL] and learning undertaken). The relationship between the variables was tested through linear regression analysis.Findings– Data analysis confirms a relationship between the learning opportunities provided by a role, and learning undertaken. Regression analysis identifies three key SRL behaviours that appear to mediate this relationship: task interest/value, task strategies and self-evaluation. Together they provide an insight into the learning processes that occur during intentional informal learning.Research limitations/implications– This quantitative study identifies a relationship between specific SRL behaviours and workplace learning undertaken in one sector. Qualitative studies are needed to understand the precise nature of this relationship. Follow-up studies could explore whether the findings are generalisable to other contexts.Practical implications– Developing a deeper understanding of how individuals manage their day-to-day learning can help shape the learning and development support provided to individual knowledge workers.Originality/value– Few studies have explored the role of self-regulation in the workplace. This study adds to our understanding of this critical element of professional learning.

Using Service Oriented Architecture for Reconceiving Quality E Training

ELearning is a fast maturing domain that involves the integration of many technologies. Learning is a knowledge intensive domain. Recent trend is to develop software applications using service oriented architectures. However current learning systems have predefined learning modules and do not take into account the competency of learner and other behavioral aspects. This paper proposes a dynamic framework for e learning systems using web services that overcomes these drawbacks. The idea is to create value added services from set of existing learning services. The approach employed utilizes the principles of service orientation that lists the software resources required for a learner depending on his/her skills, learning capability and the requirement of the organization. It customizes the learning material to each ones need. This paper is dedicated to providing improved learning opportunities for the IT industry that meet the needs of employees and enhance their knowledge and expertise level for skills relevant to their role in the software team. General Terms Service oriented Architecture

Professional Learning through Massive Open Online Courses

This study explores the role of Massive Open Online Courses (MOOCs) in supporting and enabling professional learning, or learning for work. The research examines how professionals self-regulate their learning in MOOCs. The study is informed by contemporary theories of professional learning, that argue that conventional forms of learning are no longer effective in knowledge intensive domains. As work roles evolve and learning for work becomes continual and personalised, self-regulation is becoming a critical element of professional learning. Yet, established forms of professional learning generally have not taken advantage of the affordances of social, semantic technologies to support self-regulated learning. MOOCs present a potentially useful approach to professional learning that may be designed to encourage self-regulated learning. The study is contextualised within ‘Fundamentals of clinical trials', a MOOC for health professionals designed and run by the Harvard Medical School, Harvard School of Public Health, and Harvard Catalyst, the Harvard Clinical and Translational Science Center, and offered by edX. The research design builds on the authors' previous studies in the areas of Technology Enhanced Learning and Professional Learning and in particular, research which explored the learning behaviours of education professionals in the Change 11 MOOC. The previous studies demonstrated a link between individual learners SRL profile and their goal setting behaviour in the Change 11 MOOC as well as uncovering other factors which influenced their engagement with the MOOC environment. The present study extends the original study by further focusing on specific aspects of self-regulation identified by the Change11 studies and our parallel studies of self-regulated learning in knowledge workers. The analysis of learner behaviour in the Fundamentals of Clinical Trials is complemented by additional exploration of the design considerations of the MOOC, to determine the extent to which course design can support or inhibit self-regulation of learning. The study poses three research questions: How are Massive Open Online Courses currently designed to support self-regulated learning? What self-regulated learning strategies and behaviours do professionals adopt? and How can MOOCs be designed to encourage professionals to self-regulate their learning? Validated methods and instruments from the original study will be adapted and employed. The research is unique in providing evidence around two critical aspects of MOOCs that are not well understood: the skills and dispositions necessary for self-regulated learning in MOOC environments, and how MOOCs can be designed to encourage the development and emergence of SRL behaviours.

Exploring the Effects of Blog Visit Experience on Relationship Quality

A blog was created to help cardiac illness patients and their families cope with the anxiety caused by their health problems and the subsequent treatment process. An empirical study reveals that the customer relationship management practices of the blog site affect visitors’ visit experience, their relationship learning, and how these latter two variables in turn have a significant impact on the quality of patient relationship with the physician. The study confirms the value of Web 2.0 applications in knowledge-intensive domains such as cardiac surgery.

Semantic Web and reasoning for cultural heritage and digital libraries

Cultural heritage and digital libraries are two closely related disciplines that traditionally benefit by the application of innovative information technologies. Currently, Semantic Web research has also grown satisfyingly mature to enable achieving tangible results and added-value in both these knowledgeintensive domains, in spite of the critical challenges of knowledge acquisition and reasoning about complex data. The purpose of this special issue is to put together a selection of high-quality research and development efforts in these areas that can offer an insight about the current state-of-the-art to the interested reader. Two papers in the issue deal with the idea of repurposing the FRBR standard towards semantic annotation and management of bibliographic records, revealing its importance and applicability for library curators in the Semantic Web context. “Supporting Multilingual Bibliographic Resource Discovery with Functional Requirements for Bibliographic Records” presents an FRBR-based service that enhances existing on-line library catalogs in a more semantically rich and relevant way to the user. Moreover, “FRBRML: A FRBR-based Framework for Semantic Interoperability” proposes a framework upon which legacy bibliographic data can be transformed into meaningful semantic descriptions based on the FRBR model. Semantic interoperability is a top-priority issue for cultural heritage applications, due to the need to aggregate legacy and/or disperse data within knowledgeaware services. In “Instance-based Semantic Interoperability in the Cultural Heritage” the authors thoroughly review and evaluate ontology matching methods in cultural heritage scenarios and present their lessons-learned from their experience with the STITCH project. In addition, “A Systemic Approach for Effective Semantic Access to Cultural Content” discusses a system for mapping proprietary metadata schemas to domain models within the framework of Europeana, and discusses reasoning-based techniques and optimizations for their discovery. The Semantic Web can enable novel dimensions in cultural information management and utilization. This is exemplified in the paper “How to Deal with Massively Heterogeneous Cultural Heritage Data – Lessons Learned in CultureSampo”. Here, the authors give insights to transforming and publishing existing cross-domain cultural heritage data of multiple forms as linked data, and to maintaining interoperability at a semantic level, while providing novel user interfaces for their exploitation. We are grateful to the various authors that trusted their work with this special issue. Thanks are due to professors Pascal Hitzler and Krzysztof Janowicz, Semantic Web Journal Editors-in-Chief, for their helpful remarks and support in preparing this special issue, and to the reviewers that readily shared their expertise to help make this issue successful. To what extend this may have been achieved, the reader will be the absolute judge. Semantic Web 3 (2012) 1 DOI 10.3233/SW-2012-0050 IOS Press