Journal of Information & Knowledge Management

This paper analyses the Customer Knowledge Management (CKM) conceptual structures existing within the literature, to identify its current state of research and extract from it, important elements that enable the construction of a CKM framework. To accomplish this, a six-step systematic literature review was performed, thus selecting 27 articles with CKM structures, which were fully inspected by using Thematic Analysis at the end. As main results, this study displays a detailed synthesis of the main elements for CKM and exposes a CKM framework composed of four dimensions, namely, Planning, Acquisition, Intelligence and Value Generation. Each dimension comprises specific processes and activities that can assist CKM managers and researchers in managing, collecting, analysing, storing, and sharing the customer knowledge. Finally, this research also presents a set of tools, methods and techniques that can be used in each of the framework processes.

Accurate weather prediction is always a challenge for meteorologists. This paper suggests a Deep Neural Network (DNN) model to predict minimum and maximum values of temperature based on various weather parameters such as humidity, dew point, and wind speed. Particle Swarm Optimisation (PSO) algorithm is applied to select relevant and important features of the datasets to improve the prediction accuracy of the model. The grid search algorithm is employed to determine the hyperparameters of the proposed DNN model. The statistical indicators Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, Nash–Sutcliffe model efficiency coefficient, and Correlation Coefficient are used to evaluate the accuracy of the prediction model. Performance comparison of the proposed model is performed with the Support Vector Machine (SVM) and Vector Autoregression (VAR) models. The experimental outcomes show that the proposed model optimised using PSO achieves better prediction accuracy than traditional approaches.

In order to achieve agility in software development, there is a need to ensure that the knowledge generated is seamlessly shared among the teams involved. Different contexts face unique contextual motivators and challenges towards achieving efficient knowledge sharing in software development firms. Overcoming these challenges starts from understanding the contextual nuances at play in the environment, in which knowledge sharing is desired. With increased need for ubiquitous and on-the-go information needs in agile software development projects, understanding the need for effective knowledge sharing platforms is important. The general scarcity of empirical studies has culminated into lack of in-depth global or local insights on knowledge sharing. This research investigates the different contours of knowledge sharing in a software development context in South Africa. Quantitative data collected using a questionnaire with closed-ended questions were analysed using an interpretive and deductive approach. Findings of this research reveal that job security, motivation, time constraints, psychological factors, communication, resistance to change, and rewards are core factors for knowledge sharing in software development projects. Compared with the global context, this research is aligned with other findings with new additions on the grouping of factors influencing knowledge sharing in software development projects. The study discusses the types of knowledge considered useful to share, presents appropriate ways of sharing such useful knowledge and articulates how different types of knowledge are shared in the South African context. This research contributes to the current debate on challenges in knowledge sharing within software development projects in developing world contexts and discusses how software development companies may ensure that triple constraints (time, cost and scope) are overcome.

This study aims to investigate the influence of presentation and sentiment orientation of user-generated ideas and reviews on idea adoption in open innovation communities (OICs). Drawing on the social influence theory, this study develops a research model that divides idea components into informational and normative determinants. The sentiment orientation of the idea title, description, and associated reviews is determined using a lexicon-based sentiment analysis approach. The research model is empirically tested using logistic regression analysis based on a dataset from the Microsoft community for business analytics products. The results reveal that the sentiment orientation of idea title has a negative influence on idea adoption, whilst the sentiment orientation of description has no influence on idea adoption. The sentiment orientation of the associated reviews has a positive influence on idea adoption, and this influence is moderated by the number of reviews. In addition, both idea title length and description length have a positive influence on idea adoption. These results offer several theoretical and practical implications and should therefore contribute to a better understanding of how user-generated ideas can be leveraged to drive innovation development and sustainability in OICs.

This study empirically investigated the relationship between tacit knowledge and innovation from the public sector context in Delta State, Nigeria. The use of tacit knowledge for innovation has been theoretically analysed in previous studies, but empirical studies in this field have only begun to emerge. Even so, very little research has been conducted in the public sector, even less in developing countries. Using the tacit-linked processes in the Nonaka and Takeuchi’s [Nonaka, I and K Takeuchi (1995). The Knowledge Creating Company. New York: Oxford University Press] knowledge conversion model, the study hypothesised that socialisation, externalisation and internalisation (SEI) relate with each other positively, and all have a significant positive effect on innovation. The study made use of the partial least square method for hypotheses testing with data collected from 169 mid-level health professionals from the Delta State Ministry of Health. Whilst the results show a positive relationship amongst the SEI processes, only socialisation and internalisation were found to have significant positive effects on innovation. However, despite externalisation non-significant effect on innovation, a significant indirect effect was achieved through internalisation. Together, these results provide important implications for public managers and public organisations to utilise the SEI processes in applying the tacit knowledge that has been created and shared to innovation.

The recommendation system takes the information related to the user profile or interest to suggest the user with convenient materials that the user is interested in. Most of the existing implicit methods find the user preferences and automatically recommend the desired products in the interface, but failed to generate user-oriented results. Hence, an effective product recommendation method is developed in this research using the proposed Tunicate Swarm Magnetic Optimisation Algorithm-based Black Hole Renyi Entropy Fuzzy Clustering+K-Nearest Neighbour (TSMOA-based BHrEFC+KNN) to generate more user convenient result by grouping relevant products and recommends the similar products to users with great interest. The proposed TSMOA is designed by integrating the Tunicate Swarm Algorithm (TSA) and Magnetic Optimisation Algorithm (MOA), respectively. With the entropy measure and Jaro–Winkler distance, the process of group matching and the matching sequence of visitor and query are performed more effectively that enable to achieve the sentiment classification based on the binary visitor sequence. The performance obtained by the proposed TSMOA-based BHrEFC+KNN is evaluated in terms of accuracy, True Positive Rate (TPR), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The performance of the proposed system is compared with the existing methods, such as Deep learning+Naïve–Bayes, K-medoids clustering+Long Short-Term Memory (LSTM), BHEFC+Support Vector Machine (SVM) and TSMOA-Black Hole Entropy Fuzzy Clustering (BHEFC)$+$Neural Network (NN), in which the TSMOA-BHEFC+NN obtained better results. The proposed TSMOA-based BHrEFC+KNN is 0.32%, 0.29%, 50%, and 6.44% is better than the existing TSMOA-BHEFC+NN in terms of accuracy, TPR, MAPE, and RMSE, respectively.

Cloud-based ERP systems are substantially expanding, which is expected shortly to demonstrate a significant impact on the current business model. Identifying the Critical Success Factors (CSFs) and the major challenges of the cloud-based ERP systems implementation will pave the pathway for prospective clients to adopt cloud ERP systems and take advantage of this novel IT-based cloud revolution. This research identifies the top 10 CSFs that contribute to delivering a successful cloud-based ERP systems implementation. A survey instrument was distributed to 70 enterprises using cloud-based ERP systems. The research outcomes indicate a positive and significant relationship between eight CSFs and the cloud-based ERP systems implementation. However, only two factors demonstrate a positive but not significant correlation. Overall, the results of this study show a notable impact of the CSFs on the cloud ERP systems implementation.

The cloud computing environment with a set of distributed computing resources is a suitable platform for the execution of large-scale applications. One of these applications is scientific workflow applications in which a large set of interrelated tasks are executed for a certain purpose. Scientific workflow scheduling is one of the main challenges in this area, which aims at the optimal assignment of tasks to computational resources. Given the heterogeneity of cloud computing resources, the scientific workflow scheduling is an NP-Complete problem that can be solved by heuristic methods. In this paper, an improved evolutionary algorithm called Scientific Workflow Scheduling Algorithm (SWSA) for scheduling scientific workflows in the cloud will be provided by ranking tasks and improving the initial population of tasks. The objective of this algorithm is to create a balance and an improvement in the parameters of the execution cost and workflow execution completion time. In this proposed approach, a heuristic algorithm is used to rank and generate the initial population, which increases the convergence rate. The experimental results show that SWSA is more efficient in terms of cost and execution time compared with other approaches.

The rapid development of artificial neural network techniques, especially convolutional neural networks, encouraged the researchers to adapt such techniques in the medical domain. Specifically, to provide assist tools to help the professionals in patients’ diagnosis. The main problem faced by the researchers in the medical domain is the lack of available annotated datasets which can be used to train and evaluate large and complex deep neural networks. In this paper, to assist researchers who are interested in applying deep learning techniques to aid the ophthalmologists in diagnosing eye-related diseases, we provide an optical coherence tomography dataset with collaboration with ophthalmologists from the King Abdullah University Hospital, Irbid, Jordan. This dataset consists of 21,991 OCT images distributed over seven eye diseases in addition to normal images (no disease), namely, Choroidal Neovascularisation, Full Macular Hole (Full Thickness), Partial Macular Hole, Central Serous Retinopathy, Geographic atrophy, Macular Retinal Oedema, and Vitreomacular Traction. To the best of our knowledge, this dataset is the largest of its kind, where images belong to actual patients from Jordan and the annotation was carried out by ophthalmologists. Two classification tasks were applied to this dataset; a binary classification to distinguish between images which belong to healthy eyes (normal) and images which belong to diseased eyes (abnormal). The second classification task is a multi-class classification, where the deep neural network is trained to distinguish between the seven diseases listed above in addition to the normal case. In both classification tasks, the U-Net neural network was modified and subsequently utilised. This modification adds an additional block of layers to the original U-Net model to become capable of handling classification as the original network is used for image segmentation. The results of the binary classification were equal to 84.90% and 69.50% as accuracy and quadratic weighted kappa, respectively. The results of the multi-class classification, by contrast, were equal to 63.68% and 66.06% as accuracy and quadratic weighted kappa, respectively.

Customer’s satisfaction is crucial for companies worldwide. An integrated strategy composes omnichannel communication systems, in which chabot is widely used. This system is supervised, and the key point is that the required training data are originally unlabelled. Labelling data manually is unfeasible mainly nowadays due to the considerable volume. Moreover, customer behaviour is often hidden in the data even for experts. This work proposes a methodology to find unknown entities and intents automatically using unsupervised learning. This is based on natural language processing (NLP) for text data preparation and on machine learning (ML) for clustering model identification. Several combinations for preprocessing, vectorisation, dimensionality reduction and clustering techniques, were investigated. The case study refers to a Brazilian electric energy company, with a data set of failed customer queries, that is, not met by the company for any reason. They correspond to about 30% (4,044 queries) of the original data set. The best identified intent model employed stemming for preprocessing, word frequency analysis for vectorisation, latent Dirichlet allocation (LDA) for dimensionality reduction, and mini-batch $k$-means for clustering. This system was able to allocate 62% of the failed queries in one of the seven found intents. For instance, this new labelled data can be used for the training of NLP-based chatbots contributing to a greater generalisation capacity, and ultimately, to increase customer satisfaction.

This study investigates the impact of global infection rates on social media posts during the COVID-19 pandemic. The study analysed over 179 million tweets posted between March 22 and April 13, 2020 and the global COVID-19 infection rates using evolutionary clustering analysis. Results showed six clusters constructed for each term type, including three-level $n$-grams (unigrams, bigrams and trigrams). The frequent occurrences of unigrams (“COVID-19”, “virus”, “government”, “people”, etc.), bigrams (“COVID 19”, “COVID-19 cases”, “times share”, etc.) and trigrams (“COVID 19 crisis”, “things help stop” and “trying times share”) were identified. The results demonstrated that the unigram trends on Twitter were up to about two times and 54 times more common than the bigram terms and trigram terms, respectively. Unigrams like “home” or “need” also became important as these terms reflected the main concerns of people during this period. Taken together, the present findings confirm that many tweets were used to broadcast people’s prevalent topics of interest during the COVID-19 pandemic. Furthermore, the results indicate that the number of COVID-19 infections had a significant effect on all clusters, being strong on 86% of clusters and moderate on 16% of clusters. The downward slope in global infection rates reflected the start of the trending of “social distancing” and “stay at home”. These findings suggest that infection rates have had a significant impact on social media posting during the COVID-19 pandemic.

Image inpainting is a process of reconstructing an incomplete image from the available information in a visually plausible way. In the proposed framework, existing image inpainting methods are classified in a new perspective. The information which is referred to, while reconstructing an image, is a critical factor of inpainting algorithms. Source of this information can be host image itself or an external source. The proposed framework broadly classifies inpainting algorithms into introspective and extrospective categories based on the source of information. Various parameters influencing the algorithms under these categories are identified in the proposed framework. A comprehensive list of all publicly available datasets along with the references are also summarized. Additionally, an in-depth analysis of the results obtained with the surveyed techniques is performed based on quantitative and qualitative parameters. The proposed framework aids the user in identifying the most suitable algorithm for various inpainting scenarios.

Pest detection and identification of diseases in agricultural crops is essential to ensure good product since it is the major challenge in the field of agriculture. Therefore, effective measures should be taken to fight the infestation to minimise the use of pesticides. The techniques of image analysis are extensively applied to agricultural science that provides maximum protection to crops. This might obviously lead to better crop management and production. However, automatic pest detection with machine learning technology is still in the infant stage. Hence, the video processing-based pest detection framework is constructed in this work by following six major phases, viz. (a) Video Frame Acquisition, (b) Pre-processing, (c) Object Tracking, (d) Foreground and Background Segmentation, (e) Feature Extraction, and (f) Classification. Initially, the moving frames of videos are pre-processed, and the movement of the object is tracked with the aid of the foreground and background segmentation approach via K-Means clustering. From the segmented image, a new feature evaluation termed as Distributed Intensity-based LBP features (DI-LBP) along with edges and colour are extracted. Further, the features are subjected to a classification process, where an optimised Neural Network (NN) is used. As a novelty, the training of NN will be carried out using a new Dragonfly with New Levy Update (D-NU) algorithm via updating the weight. Finally, the performance of the proposed model is analysed over other conventional models with respect to certain performance measures for both video and image datasets.