Search results

Twitter fake accounts refer to bot accounts created by third-party organizations to influence public opinion, commercial propaganda or impersonate others. The effective identification of bot accounts is conducive to accurately judge the disseminated information for the public. However, in actual fake account identification, it is expensive and inefficient to manually label Twitter accounts, and the labeled data are usually unbalanced in classes. To this end, the authors propose a novel framework to solve these problems.

In the proposed framework, the authors introduce the concept of semi-supervised self-training learning and apply it to the real Twitter account data set from Kaggle. Specifically, the authors first train the classifier in the initial small amount of labeled account data, then use the trained classifier to automatically label large-scale unlabeled account data. Next, iteratively select high confidence instances from unlabeled data to expand the labeled data. Finally, an expanded Twitter account training set is obtained. It is worth mentioning that the resampling technique is integrated into the self-training process, and the data class is balanced at the initial stage of the self-training iteration.

The proposed framework effectively improves labeling efficiency and reduces the influence of class imbalance. It shows excellent identification results on 6 different base classifiers, especially for the initial small-scale labeled Twitter accounts.

This paper provides novel insights in identifying Twitter fake accounts. First, the authors take the lead in introducing a self-training method to automatically label Twitter accounts from the semi-supervised background. Second, the resampling technique is integrated into the self-training process to effectively reduce the influence of class imbalance on the identification effect.

The purpose of this paper is to propose a methodology to analyze a large amount of unstructured textual data into categories of business environmental analysis frameworks.

This paper uses machine learning to classify a vast amount of unstructured textual data by category of business environmental analysis framework. Generally, it is difficult to produce high quality and massive training data for machine-learning-based system in terms of cost. Semi-supervised learning techniques are used to improve the classification performance. Additionally, the lack of feature problem that traditional classification systems have suffered is resolved by applying semantic features by utilizing word embedding, a new technique in text mining.

The proposed methodology can be used for various business environmental analyses and the system is fully automated in both the training and classifying phases. Semi-supervised learning can solve the problems with insufficient training data. The proposed semantic features can be helpful for improving traditional classification systems.

This paper focuses on classifying sentences that contain the information of business environmental analysis in large amount of documents. However, the proposed methodology has a limitation on the advanced analyses which can directly help managers establish strategies, since it does not summarize the environmental variables that are implied in the classified sentences. Using the advanced summarization and recommendation techniques could extract the environmental variables among the sentences, and they can assist managers to establish effective strategies.

The feature selection technique developed in this paper has not been used in traditional systems for business and industry, so that the whole process can be fully automated. It also demonstrates practicality so that it can be applied to various business environmental analysis frameworks. In addition, the system is more economical than traditional systems because of semi-supervised learning, and can resolve the lack of feature problem that traditional systems suffer. This work is valuable for analyzing environmental factors and establishing strategies for companies.

The purpose of this study is to provide a detailed overview of the role and participation of embedded librarians in the academic e-classroom. More specifically, this paper reflects the perceptions of Greek academic librarians regarding the use of learning management systems (LMSs). Furthermore, it seeks to highlight the most popular software, to list the services provided through LMSs and to determine the level of librarians’ engagement with LMSs. Finally, it investigates the challenges and benefits of their use.

Survey research was used as the methodological design. An adequate questionnaire was created for the collection of quantitative data to study the activities and experiences of academic embedded librarians.

According to the study findings, a considerable percentage of academic librarians use the potential of LMSs, indicating that embedded librarianship is the future for Greek academic libraries. However, it seems that LMSs are not fully exploited even during the pandemic when the libraries remained closed.

This study was exploratory in nature and thus its scope was limited. It was limited to embedded librarianship in academic libraries.

Embedded librarianship comes with many challenges for its practitioners; yet, it also has the potential to connect libraries and librarians directly to the overall institutional aims and enhance their positions in the academy.

The role and participation of embedded librarians in Greek academic institutions is a research area that has not been fully investigated. Therefore, this paper can give insights into this critical issue, especially during a pandemic.

The perpetual popularity of talent shows, beauty contests and all forms of competitive sport testifies to a deep desire in many of us not only for achievement, but also for public recognition of our achievement. We want to excel, and we want others to accept our excellence. We want to be stars.

The study examined the impact of feedback types through a learning management system (LMS) on employees’ training performance. The purpose of this study is to establish effective feedback on advanced technologies for promoting corporate training.

A total of 148 trainees were recruited from a multinational medical company. Employees were randomly assigned to receive feedback from shallow to more constructive details on their learning performance with LMS. Data sources included are employees’ goal setting (GS) performance evaluated by the experts and their posttest scores obtained from the LMS. A series of statistical analyses were performed to investigate the impact of feedback intervention on employees’ GS and their impacts on corporate training results.

GS has a significant impact on learning outcomes. Employees who set greater specific goals attained higher scores. Furthermore, feedback with more formative evaluation and constructive developmental advice resulted in the most significant positive influence on the relationship between participants’ GS and learning outcomes.

Organizations can benefit from delivering appropriate feedback using LMS to enhance employees’ GS and learning efficacy in corporate training.

This study is one of the first to examine the moderating effect of feedback provided by LMS on GS and online learning performance in corporate training. This study contributes to GS theory for practical application and proposes a viable method for remote learning. The current study’s findings can be used to provide educational psychological insights for training and learning in industrial contexts.

Training as an important source of dynamic capabilities (DC) is important to the performance of sports’ organisations (SO) both to athletes and to non-athletic staff. There are a variety of training delivery methods (TDMs). The purpose of this study is to determine from a set of six TDMs which one is considered to be the most suitable to enhance performance of SO.

Based on the DC theory, a cross-sectional survey from a sample of 554 workers was used to assess which TDM is considered to be the most efficient and presents higher efficacy, according to the preferences and perception of the staff.

It was concluded that: “on-the-job training” is considered to be the preferred and most effective TDM; formal/informal coaching is the second choice, in terms of perceived effectiveness and “online learning” is considered the least effective TDM. TDM’s preferences and results’ perceptions do not change according to differentiating issues such as gender, educational level of trainees or even hierarchical position.

The present study adopted a cross-sectional survey where relationships and correlations were developed continuously. Although difficult to obtain, it would have been advisable to use a survey based on longitudinal data. Results should only be considered for the purposes of the present sample, although it may be considered that they are generalizable to similar organisations and some preliminary results are raised that worth being analysed further.

The outcomes of this study will help managers of SO, according to the situation to be addressed, to choose the best TDM for their non-athletic staff, the ones that will best support their process of continuous improvement and show the best results in terms of renewal of their DC and resources.

This study highlights the training process as a source of DC contributing to overall organisation’s performance and competitive advantage. It enlarges knowledge on SO, from the pure athletic view to the managerial point of view, and operationalises training to decide the most adequate TDM to improve DC and support the success of SO. Considering that it is usually difficult to measure the concrete results of training on the organisational performance, this is also an important field of study for the management theory in the domain of strategy and human resources because the bridge considered here has not been much developed for a long time.

The paper aims to describe the application of two key service quality frameworks for improving the delivery of postgraduate research supervision. The services quality frameworks are used to identify key areas of overlap between services marketing practice and postgraduate supervision that can be used by the supervisor to improve research supervision outcomes for the student.

The paper is a conceptual and theoretical examination of the two streams of literature that proposes a supervision gap model based on the services gap literature, and the application of services delivery frameworks of co‐creation and service quality.

Services marketing literature can inform the process of designing and delivering postgraduate research supervision by clarifying student supervisor roles, setting parameters and using quality assurance frameworks for supervision delivery. The five services quality indicators can be used to examine overlooked areas of supervision delivery, and the co‐creation approach of services marketing can be used to empower student design and engaged in the quality of the supervision experience.

As a conceptual paper based on developing a theoretical structure for applying services marketing theory into the research supervision context, the paper is limited to suggesting potential applications. Further research studies will be necessary to test the field implementation of the approach.

The practical implications of the paper include implementation suggestions for applying the supervisor gaps for assessing areas of potential breakdown in the supervision arrangement.

The paper draws on two diverse areas of theoretical work to integrate the experience, knowledge and frameworks of commercial services marketing into the postgraduate research supervision literature.

Prediction is a critical task in targeted online advertising, where predictions better than random guessing can translate to real economic return. This study aims to use machine learning (ML) methods to identify individuals who respond well to certain linguistic styles/persuasion techniques based on Aristotle’s means of persuasion, rhetorical devices, cognitive theories and Cialdini’s principles, given their psychometric profile.

A total of 1,022 individuals took part in the survey; participants were asked to fill out the ten item personality measure questionnaire to capture personality traits and the dysfunctional attitude scale (DAS) to measure dysfunctional beliefs and cognitive vulnerabilities. ML classification models using participant profiling information as input were developed to predict the extent to which an individual was influenced by statements that contained different linguistic styles/persuasion techniques. Several ML algorithms were used including support vector machine, LightGBM and Auto-Sklearn to predict the effect of each technique given each individual’s profile (personality, belief system and demographic data).

The findings highlight the importance of incorporating emotion-based variables as model input in predicting the influence of textual statements with embedded persuasion techniques. Across all investigated models, the influence effect could be predicted with an accuracy ranging 53%–70%, indicating the importance of testing multiple ML algorithms in the development of a persuasive communication (PC) system. The classification ability of models was highest when predicting the response to statements using rhetorical devices and flattery persuasion techniques. Contrastingly, techniques such as authority or social proof were less predictable. Adding DAS scale features improved model performance, suggesting they may be important in modelling persuasion.

In this study, the survey was limited to English-speaking countries and largely Western society values. More work is needed to ascertain the efficacy of models for other populations, cultures and languages. Most PC efforts are targeted at groups such as users, clients, shoppers and voters with this study in the communication context of education – further research is required to explore the capability of predictive ML models in other contexts. Finally, long self-reported psychological questionnaires may not be suitable for real-world deployment and could be subject to bias, thus a simpler method needs to be devised to gather user profile data such as using a subset of the most predictive features.

The findings of this study indicate that leveraging richer profiling data in conjunction with ML approaches may assist in the development of enhanced persuasive systems. There are many applications such as online apps, digital advertising, recommendation systems, chatbots and e-commerce platforms which can benefit from integrating persuasion communication systems that tailor messaging to the individual – potentially translating into higher economic returns.

This study integrates sets of features that have heretofore not been used together in developing ML-based predictive models of PC. DAS scale data, which relate to dysfunctional beliefs and cognitive vulnerabilities, were assessed for their importance in identifying effective persuasion techniques. Additionally, the work compares a range of persuasion techniques that thus far have only been studied separately. This study also demonstrates the application of various ML methods in predicting the influence of linguistic styles/persuasion techniques within textual statements and show that a robust methodology comparing a range of ML algorithms is important in the discovery of a performant model.

The purpose of this study is to examine the continuance intentions of working professionals to pursue e-learning courses as a path for career advancement. The primary objective of this study is to ascertain the predictors of continued intentions of working professionals to pursue e-learning courses and examine if this is a trend in career development.

Perceived usefulness of e-learning, motivation and satisfaction are independent variables which are examined using a regression model as potential determinants of continued intentions to use various e-learning platforms. Data from 240 working professionals in different sectors was collected. In addition, satisfaction, motivation and perceived usefulness among the male and female respondents are compared using ANOVA.

The findings showed that motivation, satisfaction and perceived usefulness of e-learning are significant predictors and have a strong influence on the continued intentions of working professionals to pursue e-learning courses. In addition, the results showed that motivation levels while pursuing e-learning and satisfaction derived from them were higher for female professionals.

This study identifies the antecedents of the continued intentions of working professionals to pursue e-learning courses on the path of career advancement. The outcome of the study can be used by educators and e-content creators to make e-learning more engaging. Corporates can also use the results of this study to identify initiatives that can encourage the pursuit of e-learning.

This study provides an important insight exploring the antecedents of continued intentions of working professionals to pursue e-learning courses as a path of career advancement. The research contributes significantly to the understanding thought process of working professionals towards their careers.

This study proposes an approach to solve the fundamental problem in using query-based methods (i.e. searching engines and patent retrieval tools) to screen patents of information and communication technology in construction (ICTC). The fundamental problem is that ICTC incorporates various techniques and thus cannot be simply represented by man-made queries. To investigate this concern, this study develops a binary classifier by utilizing deep learning and NLP techniques to automatically identify whether a patent is relevant to ICTC, thus accurately screening a corpus of ICTC patents.

This study employs NLP techniques to convert the textual data of patents into numerical vectors. Then, a supervised deep learning model is developed to learn the relations between the input vectors and outputs.

The validation results indicate that (1) the proposed approach has a better performance in screening ICTC patents than traditional machine learning methods; (2) besides the United States Patent and Trademark Office (USPTO) that provides structured and well-written patents, the approach could also accurately screen patents form Derwent Innovations Index (DIX), in which patents are written in different genres.

This study contributes a specific collection for ICTC patents, which is not provided by the patent offices.

The proposed approach contributes an alternative manner in gathering a corpus of patents for domains like ICTC that neither exists as a searchable classification in patent offices, nor is accurately represented by man-made queries.

A deep learning model with two layers of neurons is developed to learn the non-linear relations between the input features and outputs providing better performance than traditional machine learning models. This study uses advanced NLP techniques lemmatization and part-of-speech POS to process textual data of ICTC patents. This study contributes specific collection for ICTC patents which is not provided by the patent offices.