Journal of Information & Knowledge Management

Determining the optimal number of beds in a hospital unit is often a very critical task. Patients’ number of arrivals and length of stay are random variables which necessitates the treatment with the number of patients at hospital as a stochastic process, and thus adding to the complexity of the bed sizing problem. The optimal number of beds is affected by some critical parameters such as target utilisation level, admission rate and target service level. This study applies a discrete event simulation model to approximate the true relationships between different control parameters and optimal number of beds. A goal programming model is then solved to find the optimal number of beds that maintains minimal deviation from target admission and utilisation levels. Data have been collected for the calendar year 2019 and then analysed and used in the simulation model. Mathematical relationships are then embedded in a multiobjective optimisation model that finds the optimal number of beds in an Intensive Care Unit that minimises the deviations from a pre-specified service and beds utilisation levels.

The aim of this study is to analyse the influence of interorganisational learning factors on the performance of Micro and Small Enterprises (MSEs) participating in a Local Productive Arrangement (LPA) network; specifically, the clothing arrangement located in the city of Santa Cruz do Capibaribe, in the state of Pernambuco, Brazil. Three aspects were analysed in the performance of the MSEs: cooperation, innovation, and market. For this, a quantitative survey method was employed, with a sample of 301 respondents, analysed through the modelling of structural equations of the PLS type. The results indicate a complex model with the variable interorganisational learning characterised as being of second order, as it is filled by first-order variables of reflexive characteristic, which obtained validation in the measurement and structural assumptions. The model suggests that interorganisational learning positively influences the performance of cooperation, innovation, and market of the MSEs that constitute the LPA.

This research examines the association of job attitudes (i.e. job involvement, job satisfaction, and commitment) with knowledge sharing behaviour of bank personnel through behavioural antecedents (i.e. motivation, attitude, and intentions to share knowledge). The hypothesised relationships among job attitudes (excluding job involvement), behaviour antecedents, and knowledge sharing behaviour are significant and consistent. Notably, the association of job satisfaction with the motivation to share knowledge is insignificant. The survey results are based on data from a stratified multistage cluster sample of 316 public and private sector bank professionals from Pakistan, analyzed using Partial Least Square (PLS)-Structure Equation Modelling (SEM). The research provides a framework for theoretical and practical implications in knowledge-intensive organisations to foster knowledge sharing that increases individual as well as organisational productivity. The study paves the way for future research by including knowledge-oriented leadership, culture, trust, knowledge governance, and citizenship behaviour in the current framework for analysis in diverse geographical and demographical contexts.

The profusion of documents production at an exponential rate over the web has made it difficult for the scientific community to retrieve most relevant information against the query. The research community is busy in proposing innovative mechanisms to ensure the document retrieval in a flexible manner. The document classification is a core concept of information retrieval that classifies the documents into predefined categories. In scientific domain, classification of documents to predefined category (ies) is an important research problem and supports number of tasks such as information retrieval, finding experts, recommender systems, etc. In Computer Science, the Association for Computing Machinery (ACM) categorization system is commonly used for organizing research papers in the topical hierarchy defined by the ACM. Accurately assigning a research paper to a predefined category (ACM topic) is a difficult task especially when the paper belongs to multiple topics. In this paper, we exploit the reference section of a research paper to predict the topics of the paper. We have proposed a framework called Category-Based Category Identification (CBCI) for multi-label research papers classification. The proposed approach extracted references from training dataset and grouped them in a Topic-Reference (TR) pair such as TR {Topic, Reference}. The references of the focused paper are parsed and compared in the pair TR {Topic, Reference}. The approach collects the corresponding list of topics matched with the references in the said pair. We have evaluated our technique for two datasets that is Journal of Universal Computer Science (JUCS) and ACM. The proposed approach is able to predict the first node in the ACM topic (topic A to K) with 74% accuracy for both JUCS and ACM dataset for multi-label classification.

Online reviews have received an overwhelming interest in the recent decades. Comparatively speaking, the online product questions and answers (Q&As) have received less attention than online reviews, despite that they both affect the image and the value of a project. Although online reviews and Q&As are both forms of user generated knowledge ion online communities, they may affect customers decision making differently. Furthermore, Q&As are very useful for pre-purchase information-searching and comparison shopping, especially when online product reviews either do not provide the needed answer or getting the desired information requires additional “cost” (i.e. time and effort) to sort out. Our findings show that Q&A traits had a varying effect on the product performance. We also found that review helpfulness is another important factor that affects product sale and popularity on e-commerce sites. The present study adds to existing electronic word-of-mouth (eWOM) and product review literature.

Semantic similarity quantification between concepts is one of the inevitable parts in domains like Natural Language Processing, Information Retrieval, Question Answering, etc. to understand the text and their relationships better. Last few decades, many measures have been proposed by incorporating various corpus-based and knowledge-based resources. WordNet and Wikipedia are two of the Knowledge-based resources. The contribution of WordNet in the above said domain is enormous due to its richness in defining a word and all of its relationship with others. In this paper, we proposed an approach to quantify the similarity between concepts that exploits the synsets and the gloss definitions of different concepts using WordNet. Our method considers the gloss definitions, contextual words that are helping in defining a word, synsets of contextual word and the confidence of occurrence of a word in other word’s definition for calculating the similarity. The evaluation based on different gold standard benchmark datasets shows the efficiency of our system in comparison with other existing taxonomical and definitional measures.

Traditionally, money served as a medium of financial transaction but now the system advances to the introduction of a new electronic payment through Blockchain technology known as cryptocurrency. The phenomenon of this cryptocurrency in Malaysia is very new and it is still in debate among Malaysians especially Bitcoin’s cryptocurrency. This research is to investigate the perception of generation Y and Generation X to Bitcoin. The research is conducted based on both primary data gathered from questionnaire and secondary data collected from valid sources. The results of the research indicate that the value of Bitcoin and the extending network of operations are considered as significant factors towards the perception towards Bitcoin, while security of Bitcoin has an opposite status. In conclusion, Bitcoin does have high potentials in the near future, and it will change the current monetary system, as it is classically known.

Mining is a challenging and important task in a non-stationary data stream. It is used in financial sectors, web log analysis, sensor networks, network traffic management, etc. In this environment, data distribution may change overtime and is called concept drift. So, it is necessary to identify the changes and address them to keep the model relevant to the incoming data. Many researchers have used Drift Detection Method (DDM). However, DDM is very sensitive to detect gradual drift where the detection delay is high. In this paper, we propose Adaptive Drift Detection Method (ADDM) which improves the performance of the drift detection mechanism. The ADDM uses a new parameter to detect the gradual drift in order to reduce the detection delay. The proposed method, ADDM, experiments with six synthetic datasets and four real-world datasets. Experimental results confirm that ADDM reduces the drift detection delay and false-positive rate (FPR) while preserving high classification accuracy.

Knowledge is recognised as a strategic resource and companies have started managing organisational knowledge to gain sustainable competitive advantage. Considerable efforts and investments have been made by organisations on knowledge management (KM) initiatives to achieve business excellence. The objective of KM is to create, store, extract, disseminate and make the requisite knowledge available for intelligent business-related decision-making. Extensive literature promoting KM exists, which focuses on KM factors in isolation. Empirical studies showing the interconnection between KM factors and organisational outcomes are still rare. This paper is the result of industry-specific empirical research conducted in India. Public sector units are dominant in the Indian steel sector, led by the Steel Authority of India (SAIL), which operates five integrated steel plants, and Rashtriya Ispat Nigam Limited (RNIL) operating one plant. Respondents have been selected from the Bhilai Steel Plant, a unit of SAIL and Vizag Steel Plant, the only unit of RNIL. Both units are almost contemporary in introducing KM initiatives in their organisations, circa 2002. The paper proposes a research model of KM comprising of different KM factors (enablers, processes, practices and organisational outcomes) identified from the extant literature. These are hypothesised to impact organisational performance and creativity of the firm. Hypotheses have then been tested with structural equation modelling (SEM) by using a survey. Findings of this study reveal that some KM factors have a significant impact on organisational performance and organisational creativity.

Associations rule mining along with classification rule mining are both significant techniques of mining of knowledge in the area of knowledge discovery in massive databases stored in different geographic locations of the world. Based on such combination of these two, class association rules for mining or associative classification methods have been generated, which, in far too many cases, showed higher prediction accuracy than platitudinous conventional classifiers. Motivated by the study, in this paper, we proposed a new approach, namely IHAC (Incorporating Heuristics for efficient rule generation & rule selection in Associative Classification). First, it utilises the database to decrease the search space and then explicitly explores the potent class association rules from the optimised database. This also blends rule generation and classifier building to speed up the overall classifier construction cycle. Experimental findings showed that IHAC performs better than any further associative classification methods.

This paper develops the Scopus H5-Index rankings, using the field of computer science as a case study. The challenge begins with the inconsistency of conference names. The rule-based approach is invented to automatically clean up duplicate conferences and assign unique pseudo ID for each conference. This data cleansing process is applied on conference names retrieved from both Scopus and ERA/CORE, in order to share common pseudo IDs for the sake of correlation analysis. The proposed data cleansing process is validated using ERA 2010 and CORE 2018 as references and reports the very small errors of 0.6% and 0.4%, respectively. Then, the Scopus H5-Index 2006–2010 and Scopus H5-Index 2014–2018 rankings are constructed and compared with the existing ERA 2010 and CORE 2018 rankings, respectively. The results show that the correlation within the Scopus H5-Index rankings (i.e. Scopus H5-Index 2006–2010 and Scopus H5-Index 2014–2018) is at the top of the moderate correlation band, where the correlation within the ERA/CORE rankings (ERA 2010 and CORE 2018) is at the top of the strong correlation band. While the correlations across ranking systems (i.e. Scopus H5-Index 2006–2010 vs. ERA 2010, and Scopus H5-Index 2014–2018 vs. CORE 2018) are at the bottom and middle of the moderate correlation band. It can be said that the quality assessment using the Scopus H5-Index ranking is more dynamic and quickly up-to-date when compared with the ERA/CORE ranking. Also, these two ranking systems are moderately correlated with each other for both periods of 2010 and 2018.

In recent times, Indian IT companies have been facing high attrition rates, especially with young employees having three to seven years of experience. Therefore, this study develops and tests a dynamic model of brand-endorsed employee engagement (EE) and employee retention (ER). Particularly, the carryover and temporal effects of the relationships and constructs are studied to understand how employee behaviour evolves over time. Using two waves of longitudinal data gathered from young employees ($n=405$) of Indian IT companies, the proposed conceptual model is investigated to test the temporal differences in the relationships between internal employer branding (IEB), organisational commitment, EE and ER. Additionally, the impact of employer internal social media usage on the relationships is also examined as an effective human resources (HR) intervention in the evolution process. The findings show that excluding the organisational commitment to EE relationship, the other two relationships between IEB to organisational commitment and EE to ER become stronger over time. Interestingly, while internal social media usage does not exhibit direct effect on organisational commitment or ER, it is instrumental in influencing IEB perception and EE during subsequent periods. Overall, this study offers directions to HR managers in the services sector on how to effectively use social media to engender engagement in employees and ultimately, enhance their intention to stay.

Associative Classification (AC) classifiers are of substantial interest due to their ability to be utilised for mining vast sets of rules. However, researchers over the decades have shown that a large number of these mined rules are trivial, irrelevant, redundant, and sometimes harmful, as they can cause decision-making bias. Accordingly, in our paper, we address these challenges and propose a new novel AC approach based on the RIPPER algorithm, which we refer to as ACRIPPER. Our new approach combines the strength of the RIPPER algorithm with the classical AC method, in order to achieve: (1) a reduction in the number of rules being mined, especially those rules that are largely insignificant; (2) a high level of integration among the confidence and support of the rules on one hand and the class imbalance level in the prediction phase on the other hand. Our experimental results, using 20 different well-known datasets, reveal that the proposed ACRIPPER significantly outperforms the well-known rule-based algorithms RIPPER and J48. Moreover, ACRIPPER significantly outperforms the current AC-based algorithms CBA, CMAR, ECBA, FACA, and ACPRISM. Finally, ACRIPPER is found to achieve the best average and ranking on the accuracy measure.

With the increasing advance of computer and information technologies, numerous documents have been published online as well as offline, and as new research fields have been continuingly created, users have a lot of trouble in finding their interesting documents. These documents can be in the form of blogs, research papers, and thesis. There is a heterogeneous set of documents which has information linked with each other. Traditional search is about taking an input of the query text from the user and checking if the subsequence is a part of any sentence in the set of documents and showing the set to the user. In this paper, we have proposed a Bidiection Encoding Contextual algorithm that can be applied to different types of documents and do a semantic search across the corpus. The algorithm used to understand the meaning of the word, their relative relationship between other words and provide the user with the documents that not just has the textual reference but also contain the relative meaning of the query. On the COVID-19 dataset, test been performed on the reliability of the interpretation through the function of linguistic similarities. The experimental findings demonstrate the strong association between the conceptual term interpretation of human consciousness in the role of measuring the similarity. Experiments show that the Bidirectional Encoding Contextual model has the best accuracy of 85.6% when compared with other traditional models like RNN, CNN and LSTM models.