Search results

The purpose of this paper is to enhance the performance of spammer identification problem in online social networks. Hyperparameter tuning has been performed by researchers in the past to enhance the performance of classifiers. The AdaBoost algorithm belongs to a class of ensemble classifiers and is widely applied in binary classification problems. A single algorithm may not yield accurate results. However, an ensemble of classifiers built from multiple models has been successfully applied to solve many classification tasks. The search space to find an optimal set of parametric values is vast and so enumerating all possible combinations is not feasible. Hence, a hybrid modified whale optimization algorithm for spam profile detection (MWOA-SPD) model is proposed to find optimal values for these parameters.

In this work, the hyperparameters of AdaBoost are fine-tuned to find its application to identify spammers in social networks. AdaBoost algorithm linearly combines several weak classifiers to produce a stronger one. The proposed MWOA-SPD model hybridizes the whale optimization algorithm and salp swarm algorithm.

The technique is applied to a manually constructed Twitter data set. It is compared with the existing optimization and hyperparameter tuning methods. The results indicate that the proposed method outperforms the existing techniques in terms of accuracy and computational efficiency.

The proposed method reduces the server load by excluding complex features retaining only the lightweight features. It aids in identifying the spammers at an earlier stage thereby offering users a propitious environment.

Nowadays people are connected by social media like Facebook, Instagram, Twitter, YouTube and much more. Bullies take advantage of these social networks to share their comments. Cyberbullying is one typical kind of harassment by making aggressive comments, abuses to hurt the netizens. Social media is one of the areas where bullying happens extensively. Hence, it is necessary to develop an efficient and autonomous cyberbullying detection technique.

In this paper, the authors proposed a transformer network-based word embeddings approach for cyberbullying detection. RoBERTa is used to generate word embeddings and Light Gradient Boosting Machine is used as a classifier.

The proposed approach outperforms machine learning algorithms such as logistic regression, support vector machine and deep learning models such as word-level convolutional neural networks (word CNN) and character convolutional neural networks with short cuts (char CNNS) in terms of precision, recall, F1-score.

One of the limitations of traditional word embeddings methods is context-independent. In this work, only text data are utilized to identify cyberbullying. This work can be extended to predict cyberbullying activities in multimedia environment like image, audio and video.

Purpose: The concept of sustainability in the livelihood of rural people is the central point for the discussion for policymakers. Different policies for poverty reduction, developing economies, and environment management are not capable of using multimedia technology for rural entrepreneurial development.

Need of the Study: The study analyses the impact of multi-media and tries to understand its significance for rural enterprises to contribute to developing entrepreneurship in rural areas to minimise poverty.

Methodology: This research analysed a framework that highlights that multi-media technology offers different ways to earn a sustainable livelihood by enhancing the range of advanced technology, access to information assets, increased social networks, information transfer system, and modernisation of traditional working. A total of 450 rural entrepreneurs were contacted to collect the data from 6 different divisions of Haryana through a questionnaire on 5-point scale. A purposive sampling technique was used for primary data collection.

Findings: The multi-media technology influences rural entrepreneurial development through certain organisational factors, new products and services, improved customer service, generation of employment opportunities over time, increased loyalty, and novel combination of resources within the specific context.

Practical Implications: The study concludes the capabilities may be utilised up to maximum advantages that increase with the use of multi-media technology in the rural framework.

Container throughput forecasting plays a pivotal role in strategic, tactical and operational level decision-making. The determination and analysis of the influencing factors of container throughput are observed to enhance the predicting accuracy. Therefore, for effective port planning and management, this study employs a deep learning-based method to forecast the container throughput while considering the influence of economic, environmental and social factors on throughput forecasting.

A novel multivariate container throughput forecasting method is proposed using long short-term memory network (LSTM). The external factors influencing container throughput, delineated using triple bottom line, are considered as an input to the forecasting method. The principal component analysis (PCA) is employed to reduce the redundancy of the input variables. The container throughput data of the Port of Los Angeles (PLA) is considered for empirical analysis. The forecasting accuracy of the proposed method is measured via an error matrix. The accuracy of the results is further substantiated by the Diebold-Mariano statistical test.

The result of the proposed method is benchmarked with vector autoregression (VAR), autoregressive integrated moving average (ARIMAX) and LSTM. It is observed that the proposed method outperforms other counterpart methods. Though PCA was not an integral part of the forecasting process, it facilitated the prediction by means of “less data, more accuracy.”

A novel deep learning-based forecasting method is proposed to predict container throughput using a hybridized autoregressive integrated moving average with external factors model and long short-term memory network (ARIMAX-LSTM).

The widespread use of information and communication technologies (ICTs) has had a significant effect on various groups and communities of people including micro, small and medium enterprises (MSMEs) and their owners/managers. The current study aims to analyze recent literature regarding adoption of ICTs by MSMEs. Further, it tries to locate gender within this broader context of diffusion of ICTs among MSMEs.

Using the thematic analysis approach, the research articles pertaining to six leading journals on ICTs, gender and entrepreneurship published during the time period from 2011 to 2019 are reviewed.

The literature selected for the study has been discussed under two primary categories, viz. “adoption of information and communication technologies for development (ICT4D) for business purposes” and “insights on gender in ICT4D use by MSMEs.”

The context-dependent nature of ICT use can enable future entrepreneurs to assess the scope of specific ICTs in given areas of operation. The gendered nature of ICTs helps to evaluate as well as question the empowerment potential of ICTs. The study emphasizes the need to account for historical specificities and transnational linkages in understanding access, adoption and use of ICT4D by women MSME entrepreneurs.

The study bridges together literature on ICT4D use by MSMEs and the role of gender in ICT-mediated entrepreneurial environments. While unraveling the interplay of power dynamics in such environments, the scope for future research in terms of tapping into the content of information exchanges and exploring the implications of “dark side of internet” for women MSME entrepreneurs is also indicated.

With the growth in internet technology, the competition between the e-commerce firms has become fierce. This has forced these online vendors to consider customer-centric strategies apart from the retail strategies for generating revenue. The purpose of this paper is to propose a structural model to study the interrelationship between a formative endogenous latent variable (LV), i.e. e-commerce success, and other LVs representing the customer-oriented success factors such as website service quality (WSQ), customer support system (CSS), personalization and electronic word-of-mouth (EWOM).

The authors develop a structural model to validate the determinants of electronic commerce success. Survey-based data obtained from 265 respondents are used to validate the model hypotheses. To analyze the data, partial least squares-structural equation modeling (PLS-SEM) is performed using smartPLS 2.0 software. The results on the interrelationships between the constructs are determined using path analysis.

The data analysis results infer the impact of these success factors on e-commerce success systems. After applying bootstrapping technique, the authors observed that WSQ, CSS, personalization and EWOM have a significant positive effect on e-commerce system success (ESS). Further studies can be performed considering mobile commerce and their critical success factors.

The findings of the study emphasize on the importance of these four exogenous variables for e-businesses in order to achieve a competitive edge over their competitors. The study provides a detailed managerial implication with respect to each causal relationship, so as to suggest some remedial measures to gain customer market.

Here, the authors consider an empirical model which shows the determinants of ESS. To the best of the authors’ knowledge, a distinctive system success framework is modeled considering a unique combination of exogenous variables not considered by previous studies.

Cyberbullying is a visible and prominent issue in today’s society. This study aims to identify factors influencing cyberbullying, discover its consequences on society, learn strategies and practices for dealing with cyberbullying and propose a framework to control cyberbullying in an online environment.

A systematic literature review was applied to meet the study’s objectives as the research methodology. A total of 27 peer-reviewed journal papers covering the study’s variables were included to carry out the systematic review.

The findings of the study revealed that social media, advancement of technology, lack of awareness, negative use of technology and smartphones affected cyberbullying in society. The study also showed the psychological disasters of cyberbullying. Prominent psychological dangers of the cyberbullying included emotional, psychiatric, psychosomatic, mental aggression, delinquency, depression, psychological distress, frustration, isolation, violence, unhappiness, suicidal tendencies, inferiority complex, embarrassment, negative emotions, self-harming attitudes and the passions of revenge. It also provided key strategies to stop and control cyberbullying activities. Key strategies included digital literacy, social support, emotional management, strict cyber laws and effective training sessions.

The study has provided a framework to stop and control cyber bullying for social survival. The study has offered significant theoretical, social and practical implications.

This paper aims to examine the relationship between mobile phones, the internet, financial inclusion, the informal economy and poverty reduction.

The study examines the relationship between mobile phones, the internet, financial inclusion, the informal economy and poverty reduction using the system generalized method of moments approach and a panel data set of 42 African countries for the period 1995–2017.

The study shows that mobile penetration and internet usage have significant positive relationship with the informal sector. Financial inclusion has significant effects, meaning that increased financial inclusion is associated with a developed informal economy. Also, mobile penetration and internet usage play significant roles in the relationship between financial inclusion and the informal economy. Further, mobile penetration and internet usage have a significant positive relationship with poverty reduction. Similarly, financial inclusion has significant effects, meaning higher financial inclusion is associated with increased poverty reduction. The informal economy also has significant effects, suggesting that the development of the informal economy is associated with poverty reduction.

Most importantly, mobile penetration, internet usage and financial inclusion play significant roles in the link between the informal economy and poverty reduction.

This work aims to synthesize a series of novel acyclic and/or heterocyclic systems, as precursors for dyes with potential antimicrobial activity that could be used for simultaneous dyeing and antimicrobial textile finishing. Thus, a series of novel pyridine, thiophene and pyrazolo[3,4-b]pyridine derivatives were synthesized, and their antimicrobial and textile finishing properties were studied and evaluated.

The synthesis, structure elucidation and antimicrobial activities of the newly synthesized compounds based on 4,4-dicyano-3-phenyl-but-3-enoic acid phenylamide (1) were demonstrated. The minimal inhibitory concentration in μg/mL of the compounds showed significant antimicrobial activity against most of the tested organisms. On the other hand, their spectral characteristics and fastness properties were measured and evaluated. Antimicrobial activities of the dyed fabrics in terms of inhibition zones (mm) were measured and evaluated.

A series of novel heterocyclic compounds (Schemes 1-3) were synthesized based on starting material (1). Compounds (1), 2, 4a, 8a and 9c exhibited comparable or even higher antibacterial activities than the selected standards (ampicillin), while compounds 2, 3c, 3d, 4a and 8b revealed higher antifungal activities than the selected standard (cycloheximide). On the other hand, some dyes showed high antimicrobial evaluation on the dyed fabrics (nylon 66, acetate and polyester) expressed as size (mm) of inhibition zones (Tables I-IV).

Results revealed that many hydrazo and azo derivatives were synthesized from some pyridines and thiophenes. The antimicrobial evaluation and textile finishing of the newly synthesized products revealed significant and potent values of antimicrobial activity.

All the synthesized compounds were novel and most of them exhibited higher antimicrobial activities than the selected standards antibiotics, thus are valuable for simultaneous dyeing and antimicrobial functional finishing of textile fabrics.

The authors study the effect of access to smartphones on the socio-economic well-being in the case of rural base of the pyramid (BoP) women. While smartphone access may have its benefits, the paper suggests augmenting access with a sociotechnical intermediary (STI) that facilitates training and online community building to enhance the well-being outcomes.

The authors conducted a survey from three groups of women from rural West Bengal (India) – (1) who do not own smartphones, (2) who have their own smartphones and (3) who receive smartphones and STI support (over two years). The authors evaluate the effect of access to smartphones and STI support on social well-being (including structural social capital and empowerment) and economic well-being (including entrepreneurial intent and subjective economic well-being).

The analysis results suggest a high relationship between smartphone ownership and higher structural social capital, empowerment (in terms of freedom of movement) and entrepreneurial intent. The authors further find these effects to be enhanced amongst women who received smartphones and support from STI.

The authors attribute this enhanced well-being amongst women with smartphones and STI support to peer-learning and cultivation of virtual role models facilitated by the STI through creation of intra-community online groups. The results have significant policy implications for socio-economic well-being of rural BoP women.