Search results

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.

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.

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.

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.

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.

Given the widespread usage and applications of smartphones today, the proposed app classification framework will have broader implications to different Web-based application environments.

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.

The innovation in big data is increasing day by day in such a way that the conventional software tools face several problems in managing the big data. Moreover, the occurrence of the imbalance data in the massive data sets is a major constraint to the research industry.

The purpose of the paper is to introduce a big data classification technique using the MapReduce framework based on an optimization algorithm. The big data classification is enabled using the MapReduce framework, which utilizes the proposed optimization algorithm, named chicken-based bacterial foraging (CBF) algorithm. The proposed algorithm is generated by integrating the bacterial foraging optimization (BFO) algorithm with the cat swarm optimization (CSO) algorithm. The proposed model executes the process in two stages, namely, training and testing phases. In the training phase, the big data that is produced from different distributed sources is subjected to parallel processing using the mappers in the mapper phase, which perform the preprocessing and feature selection based on the proposed CBF algorithm. The preprocessing step eliminates the redundant and inconsistent data, whereas the feature section step is done on the preprocessed data for extracting the significant features from the data, to provide improved classification accuracy. The selected features are fed into the reducer for data classification using the deep belief network (DBN) classifier, which is trained using the proposed CBF algorithm such that the data are classified into various classes, and finally, at the end of the training process, the individual reducers present the trained models. Thus, the incremental data are handled effectively based on the training model in the training phase. In the testing phase, the incremental data are taken and split into different subsets and fed into the different mappers for the classification. Each mapper contains a trained model which is obtained from the training phase. The trained model is utilized for classifying the incremental data. After classification, the output obtained from each mapper is fused and fed into the reducer for the classification.

The maximum accuracy and Jaccard coefficient are obtained using the epileptic seizure recognition database. The proposed CBF-DBN produces a maximal accuracy value of 91.129%, whereas the accuracy values of the existing neural network (NN), DBN, naive Bayes classifier-term frequency–inverse document frequency (NBC-TFIDF) are 82.894%, 86.184% and 86.512%, respectively. The Jaccard coefficient of the proposed CBF-DBN produces a maximal Jaccard coefficient value of 88.928%, whereas the Jaccard coefficient values of the existing NN, DBN, NBC-TFIDF are 75.891%, 79.850% and 81.103%, respectively.

In this paper, a big data classification method is proposed for categorizing massive data sets for meeting the constraints of huge data. The big data classification is performed on the MapReduce framework based on training and testing phases in such a way that the data are handled in parallel at the same time. In the training phase, the big data is obtained and partitioned into different subsets of data and fed into the mapper. In the mapper, the features extraction step is performed for extracting the significant features. The obtained features are subjected to the reducers for classifying the data using the obtained features. The DBN classifier is utilized for the classification wherein the DBN is trained using the proposed CBF algorithm. The trained model is obtained as an output after the classification. In the testing phase, the incremental data are considered for the classification. New data are first split into subsets and fed into the mapper for classification. The trained models obtained from the training phase are used for the classification. The classified results from each mapper are fused and fed into the reducer for the classification of big data.

Hotel classification systems are used to convey information about facilities and services. Yet, they have been prone to criticism for overemphasizing facilities at the expense of other matters of importance to service quality. In contrast, online travel agents (OTAs) use innovative methods to evaluate satisfaction with hotels. Conventional systems will lose relevance if they do not step up to consider service aspects associated with customer satisfaction. This chapter probes five hotel classification systems along with one OTA and leverages the literature to propose an improved framework classification. This is based on nine critical areas that include service quality, infrastructure, facilities and services, human resources, sustainability, safety and security, accessibility, quality systems, and online hotel ratings.

Digital tools have been used to document cultural heritage with high-quality imaging and metadata. However, some of the historical assets are totally or partially unlabeled and some are physically damaged, which decreases their attractiveness and induces loss of value. This paper introduces a new framework that aims at tackling the cultural data enrichment challenge using machine learning.

This framework focuses on the automatic annotation and metadata completion through new deep learning classification and annotation methods. It also addresses issues related to physically damaged heritage objects through a new image reconstruction approach based on supervised and unsupervised learning.

The authors evaluate approaches on a data set of cultural objects collected from various cultural institutions around the world. For annotation and classification part of this study, the authors proposed and implemented a hierarchical multimodal classifier that improves the quality of annotation and increases the accuracy of the model, thanks to the introduction of multitask multimodal learning. Regarding cultural data visual reconstruction, the proposed clustering-based method, which combines supervised and unsupervised learning is found to yield better quality completion than existing inpainting frameworks.

This research work is original in sense that it proposes new approaches for the cultural data enrichment, and to the authors’ knowledge, none of the existing enrichment approaches focus on providing an integrated framework based on machine learning to solve current challenges in cultural heritage. These challenges, which are identified by the authors are related to metadata annotation and visual reconstruction.

This paper aims to present an alternative practical framework to classify the skill and knowledge of the individual trainees by comparing it with the expert in an organization. This framework gives the benefit to the organization in order to know the ability level of the personnel and to be able to provide the personnel development method both in academic learning and workplace learning.

This research develops the framework based on relevant methodologies. Competency-Based Development is applied to investigate the knowledge and skill of the specific task. Knowledge Engineering is used to capture the experiences and construct knowledge model from relevance parties. Capability Maturity Model is then adapted to develop the capability and maturity level of the personnel. It can then be used to cluster the knowledge and skill. Finally, the Substation Maintenance Department of Provincial Electricity Authority (PEA), Thailand, is selected as a case study to test the proposed framework.

The results have shown that the proposed framework can be utilized to identify the capability level of the individual personnel. Furthermore, the appropriate maturity development of the employees in each level can also be identified. This proposed framework provides better results when comparing to the current PEA competency model, as the criteria in this framework are systematically derived from experts rather than relying solely on the proficiency level. Although, this framework was tested with the switchgear maintenance task, the results and its systematic approach have indicated that it can also be used to develop the capability maturity model for other fields of work.

The main originality of this research is the proposed competency analysis table, which integrates human resource development with knowledge management, risks management and management information system. Rather than performing these tasks separately for continuous quality improvement, organization can practically plan and perform the quality improvement-related tasks spontaneously. Moreover, the application of the capability maturity model to classify knowledge and skill of the maintenance tasks into maturity level is another academic value presented in this paper. The proposed framework gives the benefit to organization to classify the capability of the personnel. This is potentially beneficial to the human resource development personnel than traditional methods in the sense that it provides the information on how to develop the specific skill of the employees.

Collecting and analysing data on mobile service usage is increasingly complex as usage diverges between different types of devices and networks. The purpose of this paper is to suggest and apply a holistic framework that helps in designing mobile service usage research as well as in communicating, positioning, and comparing research results.

The framework was constructed based on longitudinal and cross‐sectional mobile service usage measurements carried out in Finland annually in 2005‐2008, covering 80‐90 percent of all mobile users and service usage. Broad use of multiple data collection methods and measurement points enabled data and method triangulation, as well as analysis and comparison of their scopes and limitations.

The paper suggests a holistic framework for analysing mobile services, relying on service science approach. For measurements and analysis, mobile services are decomposed into four technical components: devices, applications, networks, and content. The paper further presents classifications for each component and discusses their relationships with possible measurement points. The framework is applied to mobile browsing usage studies.

Future work includes adding an actors dimension to the framework in order to analyse their roles in the value networks providing mobile services. Extending the framework to Internet services more generally is also possible.

The paper presents an original, broadly applicable framework for designing mobile service usage research, and communicating, positioning, and comparing research results. The framework helps academics and practitioners to design and to recognise the limitations of mobile service usage studies, and to avoid misinterpretations based on insufficient data.

The purpose of this paper is to explore how the use of social media by citizens has impacted the traditional conceptualization and operationalization of political participation in the society.

This study is based on Teorell et al.’s (2007) classification of political participation which is modified to suit the current context of social media. The authors classified 15,460 tweets along three parameters suggested in the framework with help of supervised text classification algorithms.

The analysis reveals that Activism is the most prominent form of political participation undertaken by people on Twitter. Other activities that were undertaken include Formal Political participation and Consumer participation. The analysis also reveals that identity of participant does not play a classifying role as expected from the theoretical framework. It was found that the social media as a platform facilitates new forms of participation which are not feasible offline.

The current work considers only the microblogging platform of Twitter as the data source. For a more comprehensive insight, analysis of other social media platforms is also required.

To the best of the authors’ knowledge, this is one of the few analyses where such a large database covering multiple social media events has been created and analysed using supervised text classification algorithms. A large proportion of previous studies on social media have been based on case study and have limited analysis to only a particular event on social media. Although there exist a few works that have studied a vast and varied collection of social media data (Gaby and Caren, 2012; Shirazi, 2013; Rane and Salem, 2012), such efforts are few in number. This study aims to add to that stream of work where a wider and more generalized set of social media data is studied.

Despite the common understanding that business model (BM) innovation is of vital importance for securing competitive positioning in the market place, managers still seem to lack appropriate frameworks and tools which can support them in renewing and rejuvenating their company’s existing BM. The purpose of this paper is to develop a structural and comprehensive toolbox of available BM configurations, from which companies can choose, to innovate their BM upon, and to design an appropriate BM innovation framework which can facilitate them in re-designing, selecting, and implementing new BM configuration possibilities.

A structured literature review is conducted to identify all the relevant BM configurations. Then, a value driver analysis is performed to group these BM configurations into appropriate categories. Finally, an ontological classification scheme and a structural and workable process, i.e. a BM innovation framework, are inductively developed.

The paper systematically develops a list of 71 BM configurations and groups them into an ontological classification scheme according to five groups: Value Proposition, Value Segment, Value Configuration, Value Network, and Value Capture. The paper illustrates how the BM innovation framework, enabled by this ontological classification scheme, provides a platform for identifying BM innovation routes for companies, allowing managers to envisage radical, disruptive, and new-to-the-world BM configuration ideas, or apply existing configurations from other industrial settings in what may be deemed new-to-the-industry innovation.

The paper enriches the amount of potential BM configurations available for managers to choose from when innovating their BMs, and extends the analysis to five core BM configuration categories. Moreover, the BM innovation framework suggested highlights the strong relationships among the value drivers, thus presenting the opportunity for managers to assess potential conflicts or synergies between various value drivers, and to align the BM management process as a whole.

The purpose of this paper is to review the literature on customer relationship management (CRM) to obtain a comprehensive framework of mutually exclusive CRM research areas and sub‐areas free of all potentially disruptive factors (plethora of CRM definitions, personal judgments, etc.).

The keywords reported in 396 CRM articles published during the period 2000‐2006 are used to uncover first a great number of detailed keyword sub‐groups and, by subject summation, the CRM‐related research areas. This classification scheme is considered unbiased, in contrast with any direct classification of articles alone among CRM research areas fixed in advance.

An up‐to‐date conceptual and functional CRM framework emerges, consisting of a total of nine distinct research areas having their own weights, importance and popularity among the research community. Newly emerging CRM research areas are self‐identified as attracting the interest of the researchers and managers.

Keywords are activated, for a first time, as an added value characteristic reflecting genuinely the authors' beliefs about the subject content fields of their articles, important enough to reveal a self‐supported and self‐weighted unbiased and exhaustive CRM framework, useful to researchers and marketing practitioners. The paper offers strong evidence that e‐CRM is too complex to be comprehensively classified by mere procedures and simple criteria alone.

This study aims to investigate the decisions related to business aspects of cloud computing and discuss the research density, models/techniques used and identify opportunities for future work.

In this paper, 155 research articles shortlisted through a systematic review were analyzed and a classification framework was developed. Using this framework, the research density is discussed and a detailed review of four widely researched decision themes is provided.

It was found that current research on business aspects is spread across 23 decision themes. The distribution, however, is skewed with 50 per cent pertaining to just four themes, namely, pricing, markets, sourcing and adoption. Simulation appears to be the preferred modeling approach. Decision themes in consumer behavior, sustainability, auditing and culture offer opportunities for future research.

The classification framework organizes extant research on applied models and allows researchers to identify potential avenues for application, improvement and development of models to support business decisions. The review is limited to academic articles and does not include industry reports.

Practitioners can readily understand various perspectives relevant to a decision theme such as pricing or sourcing, seek and use associated models such as simulation, optimization and game theory to support their decision-making.

Most of the extant review paper deal with cloud computing technology. This study is the first systematic review on the models applied to business aspects of cloud computing. This study provides a classification framework and explicitly lists associated decision themes, models/techniques and opportunities.