Journal of Systems and Information Technology

Teubner, Timm

2018 Journal of Systems and Information Technology

doi: 10.1108/jsit-11-2017-0104

The purpose of this paper is to explore Airbnb’s inherent network structure emerging from transactions between hosts and guests and provide comprehensive background information on the underlying data basis.Design/methodology/approachThe analysis is based on actual Airbnb data from 16 major US cities (Asheville, Austin, Boston, Chicago, Denver, Los Angeles, Nashville, New Orleans, New York City, Oakland, Portland, San Diego, San Francisco, Santa Cruz, Seattle and Washington DC), available at InsideAirbnb.com, comprising a total of 135 thousand listings and 2.7 million transactions. The data are transformed into a graph and analyzed from a network perspective.FindingsThe web of host–guest connections on Airbnb represents a omniferous graph, that is, connecting virtually all users via relatively short distances. Hosts and guests differ markedly with regard to degree distribution. Overall, 98 per cent of all transactions represent first-time encounters.Research limitations/implicationsThis paper provides first insights into the very fabric of host–guest interactions on Airbnb from a macroscopic perspective. The platform’s network topology may be leveraged as a resource for trust-building between users. Moreover, platform operators may use network analyses to gain deeper insights into their user base. These may in turn be used to identify determinants of side-switching, deter users from platform circumvention or for churn prevention.Originality/valuePlatform ecosystems continue to expand and gain increasing economic, social and societal importance. For C2C platforms with two compartmentalized and decentral market sides (i.e. many individual providers and many individual consumers), the emerging transactional network structure has, thus, far experience almost no research attention. This analysis of Airbnb’s web of host–guest connections reveals a topology some archetypical social network properties (e.g. short distances). This structure and the knowledge about users’ positions therein yields viable cues for trust-building as well as a valuable resource for (platform) business analytics.

Thongsri, Nattaporn; Shen, Liang; Bao, Yukun; Alharbi, Ibraheem Mubarak

2018 Journal of Systems and Information Technology

doi: 10.1108/jsit-11-2017-0107

The purpose of this study was to investigate factors that influence the intention to use mobile learning (m-learning) by learners in developing countries such as Thailand. This study integrated two theories; namely, the unified theory of acceptance and use of technology (UTAUT), which focuses on technology, and uses and gratifications theory (UGT), which involves studying learners’ motivation.Design/methodology/approachApplying a quantitative research method, this study conducted a survey of 359 undergraduates. The partial least squares methods and a statistical analysis technique based on the structural equation modelling (SEM), were used to analyse the data.FindingsThe results revealed that the performance expectancy, cognitive need, affective need and social need had significant effect on intention to use m-learning. Furthermore, this study found a significant effect of the cognitive need on the performance expectancy and social need on effort expectancy.Practical implicationsThis research model has provided guidelines for the effective development of educational applications for use on mobile devices. The findings can be applied as guidelines for public organizations to develop educational strategies to further encourage the development of online learning.Originality/valueThis research closed a gap of understanding from previous studies by integrating UTAUT and UGT. The method derived from the theoretically integrated model could be applied to study the intentions for the implementation the mobile learning application from the context of developing countries such as Thailand.

Trivedi, Shrawan Kumar; Panigrahi, Prabin Kumar

2018 Journal of Systems and Information Technology

doi: 10.1108/jsit-11-2017-0105

Email spam classification is now becoming a challenging area in the domain of text classification. Precise and robust classifiers are not only judged by classification accuracy but also by sensitivity (correctly classified legitimate emails) and specificity (correctly classified unsolicited emails) towards the accurate classification, captured by both false positive and false negative rates. This paper aims to present a comparative study between various decision tree classifiers (such as AD tree, decision stump and REP tree) with/without different boosting algorithms (bagging, boosting with re-sample and AdaBoost).Design/methodology/approachArtificial intelligence and text mining approaches have been incorporated in this study. Each decision tree classifier in this study is tested on informative words/features selected from the two publically available data sets (SpamAssassin and LingSpam) using a greedy step-wise feature search method.FindingsOutcomes of this study show that without boosting, the REP tree provides high performance accuracy with the AD tree ranking as the second-best performer. Decision stump is found to be the under-performing classifier of this study. However, with boosting, the combination of REP tree and AdaBoost compares favourably with other classification models. If the metrics false positive rate and performance accuracy are taken together, AD tree and REP tree with AdaBoost were both found to carry out an effective classification task. Greedy stepwise has proven its worth in this study by selecting a subset of valuable features to identify the correct class of emails.Research limitations/implicationsThis research is focussed on the classification of those email spams that are written in the English language only. The proposed models work with content (words/features) of email data that is mostly found in the body of the mail. Image spam has not been included in this study. Other messages such as short message service or multi-media messaging service were not included in this study.Practical implicationsIn this research, a boosted decision tree approach has been proposed and used to classify email spam and ham files; this is found to be a highly effective approach in comparison with other state-of-the-art modes used in other studies. This classifier may be tested for different applications and may provide new insights for developers and researchers.Originality/valueA comparison of decision tree classifiers with/without ensemble has been presented for spam classification.

Nagaraj, Kalyan; Bhattacharjee, Biplab; Sridhar, Amulyashree; GS, Sharvani

2018 Journal of Systems and Information Technology

doi: 10.1108/jsit-09-2017-0074

Phishing is one of the major threats affecting businesses worldwide in current times. Organizations and customers face the hazards arising out of phishing attacks because of anonymous access to vulnerable details. Such attacks often result in substantial financial losses. Thus, there is a need for effective intrusion detection techniques to identify and possibly nullify the effects of phishing. Classifying phishing and non-phishing web content is a critical task in information security protocols, and full-proof mechanisms have yet to be implemented in practice. The purpose of the current study is to present an ensemble machine learning model for classifying phishing websites.Design/methodology/approachA publicly available data set comprising 10,068 instances of phishing and legitimate websites was used to build the classifier model. Feature extraction was performed by deploying a group of methods, and relevant features extracted were used for building the model. A twofold ensemble learner was developed by integrating results from random forest (RF) classifier, fed into a feedforward neural network (NN). Performance of the ensemble classifier was validated using k-fold cross-validation. The twofold ensemble learner was implemented as a user-friendly, interactive decision support system for classifying websites as phishing or legitimate ones.FindingsExperimental simulations were performed to access and compare the performance of the ensemble classifiers. The statistical tests estimated that RF_NN model gave superior performance with an accuracy of 93.41 per cent and minimal mean squared error of 0.000026.Research limitations/implicationsThe research data set used in this study is publically available and easy to analyze. Comparative analysis with other real-time data sets of recent origin must be performed to ensure generalization of the model against various security breaches. Different variants of phishing threats must be detected rather than focusing particularly toward phishing website detection.Originality/valueThe twofold ensemble model is not applied for classification of phishing websites in any previous studies as per the knowledge of authors.

Teh, Phoey Lee; Ooi, Pei Boon; Chan, Nee Nee; Chuah, Yee Kang

2018 Journal of Systems and Information Technology

doi: 10.1108/jsit-12-2017-0120

Sarcasm is often used in everyday speech and writing and is prevalent in online contexts. The purpose of this paper is to investigate the analogy between sarcasm comments from sentiment tools and the human coder.Design/methodology/approachUsing the Verbal Irony Procedure, eight human coders were engaged to analyse comments collected from an online commercial page, and a dissimilarity analysis was conducted with sentiment tools. Three constants were tested, namely, polarity from sentiment tools, polarity rating by human coders; and sarcasm-level ratings by human coders.FindingsResults found an inconsistent ratio between these three constants. Sentiment tools used did not have the capability or reliability to detect the subtle, contextualized meanings of sarcasm statements that human coders could detect. Further research is required to refine the sentiment tools to enhance their sensitivity and capability.Practical implicationsWith these findings, it is recommended that further research and commercialization efforts be directed at improving current sentiment tools – for example, to incorporate sophisticated human sarcasm texts in their analytical systems. Sarcasm exists frequently in media, politics and human forms of communications in society. Therefore, more highly sophisticated sentiment tools with the abilities to detect human sarcasm would be vital in research and industry.Social implicationsThe findings suggest that presently, of the sentiment tools investigated, most are still unable to pick up subtle contexts within the text which can reverse or change the message that the writer intends to send to his/her receiver. Hence, the use of the relevant hashtags (e.g. #sarcasm; #irony) are of fundamental importance in detection tools. This would aid the evaluation of product reviews online for commercial usage.Originality/valueThe value of this study lies in its original, empirical findings on the inconsistencies between sentiment tools and human coders in sarcasm detection. The current study proves these inconsistencies are detected between human and sentiment tools in social media texts and points to the inadequacies of current sentiment tools. With these findings, it is recommended that further research and commercialization efforts be directed at improving current sentiment tools – to incorporate sophisticated human sarcasm texts in their analytical systems. The system can then be used as a reference for psychologists, media analysts, researchers and speech writers to detect cues in the inconsistencies in behaviour and language.

Tan, Christine Nya-Ling; Ramayah, T.

2018 Journal of Systems and Information Technology

doi: 10.1108/jsit-09-2017-0071

To compete in a globally challenging environment, small and medium enterprises (SMEs) are increasingly pressured to leverage their relational capital to stay competitive. The purpose of this study is to model the KS behaviour of SMEs in an increasingly networked world through communities of practice (CoP).Design/methodology/approachData were collected using a survey instrument developed based on prior literature from SMEs operating only in the electronic manufacturing industry. A total of 120 responses were received of which only 100 were valid. SmartPLS, a second-generation analysis software, was used to analyse the model developed.FindingsThe findings indicated that affect, reward, perceived consequences and social factor were all positive predictors of KS behaviour of SMEs in communities of practice. Interestingly, the facilitating conditions were found to negatively influence KS behaviour.Practical implicationsThe findings are helpful to SMEs who are embarking on knowledge management (KM) practices in their respective companies and may be used to leverage the drivers of KM to improve more sharing behaviour that keeps SMEs competitive.Originality/valueTo the best of the authors' knowledge, few studies have explored the individual (i.e. perceived consequences, affect), social (i.e. social factor) and organisational (i.e. facilitating condition, reward) predictors of KS behaviour among CoP’s in Malaysian SMEs.