A web interface for WMN-PSODGA hybrid intelligent simulation system: performance evaluation for different mesh client distributions

Purpose The purpose of this paper is to implement a web interface for a hybrid intelligent system. By using the implemented web interface, one can find optimal assignments of mesh routers in wireless mesh networks (WMNs). This study evaluates the implemented system considering three distributions of mesh clients to solve the node placement problem in WMNs. Design/methodology/approach The node placement problem in WMNs is well known to be a computationally hard problem. Therefore, intelligent algorithms are used for solving this problem. The implemented system is a hybrid intelligent system based on meta-heuristics algorithms: particle swarm optimization (PSO) and distributed genetic algorithm (DGA). The proposed system is called WMN-PSODGA. Findings This study carried out simulations using the implemented simulation system. From the simulations results, it was found that the WMN-PSODGA system performs better for chi-square distribution of mesh clients compared with Weibull and exponential distributions. Research limitations/implications For simulations, three different distributions of mesh clients were considered. In the future, other mesh client distributions, number of mesh nodes and communication distance need to be considered. Originality/value This research work, different from other research works, implemented a hybrid intelligent simulation system for WMNs. This study also implemented a web interface for the proposed system, which make the simulation system user-friendly.

An automated mobile app labeling framework based on primary motivations for smartphone use

Purpose This paper aims to propose an automated mobile app labeling framework based on a novel app classification scheme that is aligned with users’ primary motivations for using smartphones. The study addresses the gaps in incorporating the needs of users and other context information in app classification as well as recommendation systems. Design/methodology/approach Based on a corpus of mobile app descriptions collected from Google Play store, this study applies extensive text analytics and topic modeling procedures to profile mobile apps within the categories of the classification scheme. Sufficient number of representative and labeled app descriptions are then used to train a classifier using machine learning algorithms, such as rule-based, decision tree and artificial neural network. Findings Experimental results of the classifiers show high accuracy in automatically labeling new apps based on their descriptions. The accuracy of the classification results suggests a feasible direction in facilitating app searching and retrieval in different Web-based usage environments. Research limitations/implications As a common challenge in textual data projects, the problem of data size and data quality issues exists throughout the multiple phases of experiments. Future research will extend the data collection scope in many aspects to address the issues that constrained the current experiments. Practical implications These empirical experiments demonstrate the feasibility of textual data analysis in profiling apps and user context information. This study also benefits app developers by improving app descriptions through a better understanding of user needs and context information. Finally, the classification framework can also guide practitioners in customizing products and services beyond mobile apps where context information and user needs play an important role. Social implications Given the widespread usage and applications of smartphones today, the proposed app classification framework will have broader implications to different Web-based application environments. Originality/value While there have been other classification approaches in the literature, to the best of the authors’ knowledge, this framework is the first study on building an automated app labeling framework based on primary motivations of smartphone usage.

Evolution of user navigation behavior for online news

Purpose The purpose of the study is to use web serer logs in analyzing the changes of user behavior in reading online news, in terms of desktop and mobile users. Advances in mobile technology and social media have paved the way for online news consumption to evolve. There is an absence of research into the changes of user behavior in terms of desktop versus mobile users, particularly by analyzing the server logs. Design/methodology/approach In this paper, the authors investigate the evolution of user behavior using logs from the Malaysian newspaper Berita Harian Online in April 2012 and April 2017. Web usage mining techniques were used for pre-processing the logs and identifying user sessions. A Markov model is used to analyze navigation flows, and association rule mining is used to analyze user behavior within sessions. Findings It was found that page accesses have increased tremendously, particularly from Android phones, and about half of the requests in 2017 are referred from Facebook. Navigation flow between the main page, articles and section pages has changed from 2012 to 2017; while most users started navigation with the main page in 2012, readers often started with an article in 2017. Based on association rules, National and Sports are the most frequent section pages in 2012 and 2017 for desktop and mobile. However, based on the lift and conviction, these two sections are not read together in the same session as frequently as might be expected. Other less popular items have higher probability of being read together in a session. Research limitations/implications The localized data set is from Berita Harian Online; although unique to this particular newspaper, the findings and the methodology for investigating user behavior can be applied to other online news. On another note, the data set could be extended to be more than a month. Although initially data for the year 2012 was collected, unfortunately only the data for April 2012 is complete. Other months have missing days. Therefore, to make an impartial comparison for the evolution of user behavior in five years, the Web server logs for April 2017 were used. Originality/value The user behavior in 2012 and 2017 was compared using association rules and Markov flow. Different from existing studies analyzing online newspaper Web server logs, this paper uniquely investigates changes in user behavior as a result of mobile phones becoming a mainstream technology for accessing the Web.

Deep learning based approach to unstructured record linkage

Purpose In the world of big data, data integration technology is crucial for maximising the capability of data-driven decision-making. Integrating data from multiple sources drastically expands the power of information and allows us to address questions that are impossible to answer using a single data source. Record Linkage (RL) is a task of identifying and linking records from multiple sources that describe the same real world object (e.g. person), and it plays a crucial role in the data integration process. RL is challenging, as it is uncommon for different data sources to share a unique identifier. Hence, the records must be matched based on the comparison of their corresponding values. Most of the existing RL techniques assume that records across different data sources are structured and represented by the same scheme (i.e. set of attributes). Given the increasing amount of heterogeneous data sources, those assumptions are rather unrealistic. The purpose of this paper is to propose a novel RL model for unstructured data. Design/methodology/approach In the previous work (Jurek-Loughrey, 2020), the authors proposed a novel approach to linking unstructured data based on the application of the Siamese Multilayer Perceptron model. It was demonstrated that the method performed on par with other approaches that make constraining assumptions regarding the data. This paper expands the previous work originally presented at iiWAS2020 [16] by exploring new architectures of the Siamese Neural Network, which improves the generalisation of the RL model and makes it less sensitive to parameter selection. Findings The experimental results confirm that the new Autoencoder-based architecture of the Siamese Neural Network obtains better results in comparison to the Siamese Multilayer Perceptron model proposed in (Jurek et al., 2020). Better results have been achieved in three out of four data sets. Furthermore, it has been demonstrated that the second proposed (hybrid) architecture based on integrating the Siamese Autoencoder with a Multilayer Perceptron model, makes the model more stable in terms of the parameter selection. Originality/value To address the problem of unstructured RL, this paper presents a new deep learning based approach to improve the generalisation of the Siamese Multilayer Preceptron model and make is less sensitive to parameter selection.

Reducing the filter bubble effect on Twitter by considering communities for recommendations

Purpose Social network platforms are considered today as a major communication mean. Their success leads to an unprecedented growth of user-generated content; therefore, finding interesting content for a given user has become a major issue. Recommender systems allow these platforms to personalize individual experience and increase user engagement by filtering messages according to user interest and/or neighborhood. Recent research results show, however, that this content personalization might increase the echo chamber effect and create filter bubbles that restrain the diversity of opinions regarding the recommended content. Design/methodology/approach The purpose of this paper is to present a thorough study of communities on a large Twitter data set that quantifies the effect of recommender systems on users’ behavior by creating filter bubbles. The authors further propose their community-aware model (CAM) that counters the impact of different recommender systems on information consumption. Findings The authors propose their CAM that counters the impact of different recommender systems on information consumption. The study results show that filter bubbles effects concern up to 10% of users and the proposed model based on the similarities between communities enhance recommendations. Originality/value The authors proposed the CAM approach, which relies on similarities between communities to re-rank lists of recommendations to weaken the filter bubble effect for these users.

Optimal deep recurrent neural network for sentiment grade classification

Purpose Internet has endorsed a tremendous change with the advancement of the new technologies. The change has made the users of the internet to make comments regarding the service or product. The Sentiment classification is the process of analyzing the reviews for helping the user to decide whether to purchase the product or not. Design/methodology/approach A rider feedback artificial tree optimization-enabled deep recurrent neural networks (RFATO-enabled deep RNN) is developed for the effective classification of sentiments into various grades. The proposed RFATO algorithm is modeled by integrating the feedback artificial tree (FAT) algorithm in the rider optimization algorithm (ROA), which is used for training the deep RNN classifier for the classification of sentiments in the review data. The pre-processing is performed by the stemming and the stop word removal process for removing the redundancy for smoother processing of the data. The features including the sentiwordnet-based features, a variant of term frequency-inverse document frequency (TF-IDF) features and spam words-based features are extracted from the review data to form the feature vector. Feature fusion is performed based on the entropy of the features that are extracted. The metrics employed for the evaluation in the proposed RFATO algorithm are accuracy, sensitivity, and specificity. Findings By using the proposed RFATO algorithm, the evaluation metrics such as accuracy, sensitivity and specificity are maximized when compared to the existing algorithms. Originality/value The proposed RFATO algorithm is modeled by integrating the FAT algorithm in the ROA, which is used for training the deep RNN classifier for the classification of sentiments in the review data. The pre-processing is performed by the stemming and the stop word removal process for removing the redundancy for smoother processing of the data. The features including the sentiwordnet-based features, a variant of TF-IDF features and spam words-based features are extracted from the review data to form the feature vector. Feature fusion is performed based on the entropy of the features that are extracted.

Representation and presentation of knowledge and processes – an integrated approach for a dynamic communication-intensive environment

Purpose Knowledge- and communication-intensive domains still long for a better support of creativity that considers legal requirements, compliance rules and administrative tasks as well, because current systems focus either on knowledge representation or business process management. The purpose of this paper is to discuss our model of integrated knowledge and business process representation and its presentation to users. Design/methodology/approach The authors follow a design science approach in the environment of patent prosecution, which is characterized by a highly standardized, legally prescribed process and individual knowledge study. Thus, the research is based on knowledge study, BPM, graph-based knowledge representation and user interface design. The authors iteratively designed and built a model and a prototype. To evaluate the approach, the authors used analytical proof of concept, real-world test scenarios and case studies in real-world settings, where the authors conducted observations and open interviews. Findings The authors designed a model and implemented a prototype for evolving and storing static and dynamic aspects of knowledge. The proposed solution leverages the flexibility of a graph-based model to enable open and not only continuously developing user-centered processes but also pre-defined ones. The authors further propose a user interface concept which supports users to benefit from the richness of the model but provides sufficient guidance. Originality/value The balanced integration of the data and task perspectives distinguishes the model significantly from other approaches such as BPM or knowledge graphs. The authors further provide a sophisticated user interface design, which allows the users to effectively and efficiently use the graph-based knowledge representation in their daily study.

Application of a methodological approach to compare ontologies

Purpose This study aims to the OQuaRE quality model to the developed methodology. Design/methodology/approach Ontologies are formal, well-defined and flexible representations of knowledge related to a specific domain. They provide the base to develop efficient and interoperable solutions. Hence, a proliferation of ontologies in many domains is unleashed. Then, it is necessary to define how to compare such ontologies to decide which one is the most suitable for the specific needs of users/developers. As the emerging development of ontologies, several studies have proposed criteria to evaluate them. Findings In a previous study, the authors propose a methodological process to qualitatively and quantitatively compare ontologies at Lexical, Structural and Domain Knowledge levels, considering correctness and quality perspectives. As the evaluation methods of the proposal are based on a golden-standard, it can be customized to compare ontologies in any domain. Practical implications To show the suitability of the proposal, the authors apply the methodological approach to conduct comparative studies of ontologies in two different domains, one in the robotic area, in particular for the simultaneous localization and mapping (SLAM) problem; and the other one, in the cultural heritage domain. With these cases of study, the authors demonstrate that with this methodological comparative process, we are able to identify the strengths and weaknesses of ontologies, as well as the gaps still needed to fill in the target domains. Originality/value Using these metrics and the quality model from OQuaRE, the authors are incorporating a standard of software engineering at the quality validation into the Semantic Web.

A study on time models in graph databases for security log analysis

Purpose For aiding computer security experts in their study, log files are a crucial piece of information. Especially the time domain is very important for us because in most cases, timestamps are the only linking points between events caused by attackers, faulty systems or simple errors and their corresponding entries in log files. With the idea of storing and analyzing this log information in graph databases, we need a suitable model to store and connect timestamps and their events. This paper aims to find and evaluate different approaches how to store timestamps in graph databases and their individual benefits and drawbacks. Design/methodology/approach We analyse three different approaches, how timestamp information can be represented and stored in graph databases. For checking the models, we set up four typical questions that are important for log file analysis and tested them for each of the models. During the evaluation, we used the performance and other properties as metrics, how suitable each of the models is for representing the log files’ timestamp information. In the last part, we try to improve one promising looking model. Findings We come to the conclusion, that the simplest model with the least graph database-specific concepts in use is also the one yielding the simplest and fastest queries. Research limitations/implications Limitations to this research are that only one graph database was studied and also improvements to the query engine might change future results. Originality/value In the study, we addressed the issue of storing timestamps in graph databases in a meaningful, practical and efficient way. The results can be used as a pattern for similar scenarios and applications.