Journal of Information & Knowledge Management

Over the last decade, collaboration and secure information-sharing (SIS) have been studied in the context of supply chain management (SCM) to determine their influence on improving a business’s performance and profitability. Collaboration refers to the firms working together to accomplish a particular objective, whereas SIS is a vital technology which permits the firms and the enablers of a supply chain to be integrated. In this paper, these aspects and their impacts on SCM are reviewed. A conceptual model with a set of hypotheses for measuring the effects of collaboration and information-sharing on SCs, which demonstrate their effective roles in SCM, is proposed.

The purpose of this study is to analyse the structure of social network co-occurrence and co-authorship of scientific documents of social innovation which are indexed in Scopus database. By using scientometric and network analysis techniques, the records were retrieved and integrated. It has been used a combination of software packages, including VOSviewer, Gephi, HistCite, Publish or Perish and NodeXL, for data analysis and mapping. Analysing all keywords shows that the most important keywords, based on frequency distribution, are innovation, sustainable growth and social entrepreneurship. Thematic mapping of the keywords using co-words analysis technique indicates that the topics innovation, social services and social change had top ranking in degree centrality, closeness centrality and betweenness indicators. The analysis of the co-authorship network of the field demonstrated that it is disconnected and sparse. Moreover, the total number of citations was 8,350. Mapping the knowledge structure of social innovation papers extracted from Scopus database could help to represent and visualise the thematic structure of research in the field of Social Science and Knowledge Studies and identify more specific research focuses within this field. It should be noted that in this study, the importance of concepts such as innovation, sustainable development and social entrepreneurship has been confirmed by reviewing the literature on these issues.

In the construction industry, safety has always been a persistent issue. The importance of safety knowledge for construction was highlighted by literature and practices. This study aimed to understand safety knowledge management (KM) commitments, strategies, and tools being used in Indian construction organisations. A survey was conducted among safety managers/heads in eight leading Indian construction contractors operating in a global construction market. The results indicated that out of eight companies, safety KM systems were available in seven companies and one was looking to implement it. All the organisations consider safety KM as the strategic assets for their companies and were aware of safety KM’s benefits. Email, Internet, small-group meetings and brainstorming were considered the most important tools to transfer safety knowledge among these organisations. Out of eight, six contracting organisations were aware that costly errors occurred at their companies when safety knowledge was not available when and where it was needed. Hence, safety knowledge sharing culture should be cultivated to enhance the safety performance of contracting companies. The findings may be used to establish standards to facilitate safety KM as an initial point for the government. This study would serve as a foundation for companies to enhance safety performance by improving their safety KM systems.

Customer Relationship Management (CRM) is a systematic way of working with current and prospective customers to manage long-term relationships and interactions between the company and customers. Recently, Big Data has become a buzzword. It consists of huge data repositories, having information collected from online and offline resources, and it is hard to process such datasets with traditional data processing tools and techniques. The presented research work tries to explore the potential of Big Data to create, optimise and transform an insightful customer relationship management system by analysing large amount of datasets for enhancing customer life cycle profitability. In this research work, a dataset, “Book Crossing” is used for Big Data processing and execution time analysis for simple and complex SQL queries. This research tries to analyse the impact of data size on the query execution time for one of the majorly used Big Data frameworks, namely Apache Spark. It is a recently developed in-memory Big Data processing framework with a SPARK SQL module for efficient SQL query execution. It has been found that Apache-Spark gives better results with large size datasets compare to small size datasets and fares better as compared to Hadoop, one of the majorly used Big Data Frameworks (based on qualitative analysis).

Two famous matrix factorization techniques, the Singular Value Decomposition (SVD) and the Nonnegative Matrix Factorization (NMF), are popularly used by recommender system applications. Recommender system data matrices have many missing entries, and to make them suitable for factorization, the missing entries need to be filled. For matrix completion, we use mean, median and mode as three different cases of imputation. The natural clusters produced after factorization are used to formulate simple out-of-sample extension algorithms and methods to generate recommendation for a new user. Two cluster evaluation measures, Normalized Mutual Information (NMI) and Purity are used to evaluate the quality of clusters.

In recent years, there exist few difficulties for textile industries to predict the yarn nep index for small data and data with mutation. To fill this gap, a yarn nep prediction method combining grey correlation analysis and nearest-neighbour prediction method is proposed. In this paper, 26 indicators such as the raw cotton quality indicators and key process parameters are used as the input of the prediction model for yarn nep. The experimental results show that the relative error of the new method is lower than 10%, while the relative error of the individual data predicted by the traditional three-layer BP neural network is very large. Compared with the BP neural network, the average relative error and root-mean-square error of our proposed method are smaller, while the data are stable and the volatility is small. The prediction performance meets the user’s requirements. The effectiveness of the proposed model is proved.

Purpose — Emotion is one of the key factors affecting creativity. In the field of marketing research, researchers generally begin to explore how to make rational use of customers” negative emotions to contribute to companies’ innovation process. However, the existing views are still divergent. Design/methodology/approach — To explore the relationship between customers’ negative emotions and creativity, we construct a research model from the perspective of self-determination Theory and Resource Preservation Theory, Based on this model, we conducted an empirical study with 401 participants. Findings: — We found that there is an inverse U-shaped relation between negative emotion and creativity. And we further verified the mediating role of customer intrinsic motivation and the moderating role of innovation self-efficacy. Originality/value — The understanding of the nonlinear relationship between emotion and creativity may provide valuable theoretical contributions to the research of creativity, and provide practical guidance for the design of innovative activities.

This study examines the relationship between the research performance and the hierarchical staff-mix by rank (or staff-mix categories) for academics in a research-oriented system. A supervised learning approach is employed to classify academics on the basis of their research performance and the association between this classification and the staff-mix categories is measured using the Somer’s $D$ coefficient. Although there have been other studies on research performance for such a system based on the volume-based indicators of research performance, this is the first study that assesses the researchers’ position in the academic reward structure on the basis of research performance. The Scopus database is used as a collection of individual productivity in research. A case-study is presented on a cross-section of academics in the mathematics discipline from different federal universities in Nigeria. The results show that there is a dearth of outstanding scientists in the system and that there is a weak association between research performance and the staff-mix categories. The need for scientific collaboration by way of a continuous collegial interaction between the outstanding scientists and the emerging scholars in the system is suggested.

In the medical field, ontologies are mainly used to standardise the coding of knowledge, either during the drafting phase of documents or during subsequent processing intended to give them a format which makes them usable for automatic processing. In this sense, they have a normative role analogous to the classical medical terminologies (in particular thesauri): to set up a common vocabulary and to make use of shared representations and concepts, in order to allow the interoperability of documents and medicals information systems. Medical and biomedical data play a very important role in the medical field. They solve many of the problems encountered during the diagnosis of diseases and in the prescription medical treatments. The objective of this paper is to develop ontology for the field of medical analyses in an attempt to facilitate the tasks of the various actors in the medical field, namely: doctors, laboratory assistants and patients. It also endeavours to improve the care of patients and facilitate the various acts of health professionals, the purpose of which is to aid in decision-making in the treatment of a disease. To this end, we followed the so-called METHONTOLOGY based on the phases ranging from the needs specification to the evaluation and documentation of this ontology of medical analysis.

Spoken language identification (LID) is the identification of language present in a speech segment despite its size (duration and speed), ambiance (topic and emotion), and moderator (gender, age, demographic region). Information Technology has touched new vistas for a couple of decades mostly to simplify the day-to-day life of humans. One of the key contributions of Information Technology is the application of Artificial Intelligence to achieve better results. The advent of artificial intelligence has given rise to a new branch of Natural Language Processing (NLP) called Computational Linguistics, which generates frameworks for intelligently manipulating spoken language knowledge and has brought human–machine into a new stage. In this context, speech has arisen to be one of the imperative forms of interfaces, which is the basic mode of communication for us, and generally the most preferred one. Recognition of the spoken language is a frontend for several technologies, like multiple languages conversation systems, expressed translation software, multilingual speech recognition, spoken word extraction, speech production systems. This paper reviews and summarises the different levels of information that can be used for language identification. A broad study of acoustic, phonetic, and prosody features has been provided and various classifiers have been used for spoken language identification specifically for Indian languages. This paper has investigated various existing spoken language identification models implemented using prosodic, phonotactic, acoustic, and deep learning approaches, the datasets used, and performance measures utilized for their analysis. It also highlights the main features and challenges faced by these models. Moreover, this review analyses the efficiency of the spoken language models that can help the researchers to propose new language identification models for speech signals.

Voice assistants like Siri, Google Assistant and Alexa are used widely across the globe for home automation. They require the use of unique phrases, also known as hotwords, to wake them up and perform an action like “Hey Alexa!”, “Ok, Google!”, “Hey, Siri!”. These hotword detectors are lightweight real-time engines whose purpose is to detect the hotwords uttered by the user. However, existing engines require thousands of training samples or is closed source seeking a fee. This paper attempts to solve the same, by presenting the design and implementation of a lightweight, easy-to-implement hotword detection engine based on few-shot learning. The engine detects the hotword uttered by the user in real-time with just a few training samples of the hotword. This approach is efficient when compared to existing implementations because the process of adding a new hotword to the existing systems requires enormous amounts of positive and negative training samples, and the model needs to retrain for every hotword, making the existing implementations inefficient in terms of computation and cost. The architecture proposed in this paper has achieved an accuracy of 95.40%.

Support vector machine (SVM) is a machine learning method widely used in solving binary data classification problems due to its performance. Nevertheless, in practical problems of classification, there are often cases of the presence of more than two classes of objects in the original dataset. The paper considers a solution to the problem of SVM multiclass with the aim to increase the data classification quality based on a new way of hybridisation between SVM and $k$-nearest neighbour (KNN) algorithms. The first phase of the approach is called the filtering phase. At this level, the feature space is split into two classes separated by a hyperplane. In the next step called review, we generate a second hyperplane, then we calculate the distance between each test pattern and the second hyperplane in the feature space using e.g. the KNN function. The result of the two phases is three classes instead of two produced by the conventional SVM. For evaluation purposes, dataset experiments are conducted on seven benchmark datasets that have high dimensionality and large size. Numerical experiments show that the 3SVM approach can improve not only the accuracy compared to other multiclass SVM approaches, but also the precision, recall, and $F_1$-score.