Research activities per year filter by: Publication Year
(Descending) Articles
Publication Date: 2025
Simulation and Gaming (1552826X)
Background: Gamification is widely used to enhance engagement, motivation, and performance across domains such as education, health, and business. However, one-size-fits-all designs often fail to address the multidimensional nature of user characteristics, resulting in inconsistent outcomes. Most personalization strategies focus on single traits (e.g., player type) and neglect personality, cultural, and persuasive factors. This study proposes a machine learning–based framework that integrates a comprehensive user model to predict and personalize eight categories of gamification elements. Methods: Survey data from 260 participants were collected via questionnaires measuring demographics, personality traits (NERIS), cultural dimensions (Hofstede), persuasive strategies (Cialdini), and player types (HEXAD), along with preferences for eight gamification element categories. Preprocessing steps included discretization, SMOTE balancing, and ANOVA F-value feature selection. Six classifiers, Logistic Regression, Decision Tree, Random Forest, SVM, Naïve Bayes, and XGBoost, were trained and evaluated with 10-fold cross-validation. A gamified image-labeling application was implemented in two versions: a generic design and a personalized design based on model predictions. A between-subject experimental evaluation with 80 participants compared both versions on six engagement and satisfaction metrics. Results: In the two-class prediction setting, Random Forest achieved the highest performance (accuracy = 0.852, F1-score = 0.855), while SVM slightly outperformed in the three-class setting (accuracy = 0.768, F1-score = 0.764). Gender consistently emerged as a top predictor, followed by personality traits, cultural dimentions, persuasive strategies, and player types. Experimental evaluation showed significant improvements for the personalized version across all six metrics, with gains of 41% (performance satisfaction), 40% (impact on satisfaction), 30% (appeal), 41% (enjoyment of personalization), 43% (encouragement for additional activities), and 31% (motivation). Conclusion: Integrating multidimensional user characteristics with machine learning enables accurate prediction of gamification preferences and significantly improves user experience. This approach addresses the limitations of one-size-fits-all gamification, providing a scalable, data-driven framework for delivering personalized, impactful designs. © The Author(s) 2025
Publication Date: 2025
Multimedia Tools and Applications (13807501) 84(11)pp. 9713-9747
Today, raising security awareness among users is one of the most effective preventive cybersecurity strategies. Generally, the current level of security awareness in the organization is measured through standard questionnaires. However, this method suffers from poor participant engagement and low precision due to the explicit evaluation and misunderstandings of the questions. To address these issues, we present a serious video game called “myREACH” to measure the player’s security awareness about ransomware. To the best of our knowledge, this is the first attempt to develop a serious game for measuring security awareness. myREACH has been compared to the standard questionnaire for measuring security awareness about ransomware, known as RSAM. The results obtained from a sample of 172 participants indicate that, in 3 out of 9 categories, the game and questionnaire measurements yield similar results. However, in 5 out of 9 categories, the game measurement is superior. For the remaining category, it is inconclusive whether the game or questionnaire assessment is better. Furthermore, self-report measurements indicate that the temporal and mental demands of playing myREACH and completing the RSAM are the same. The overall performance during playing myREACH is 9% better than completing the RSAM, and participants are 15% more satisfied with the game compared to the questionnaire. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
Publication Date: 2024
pp. 254-265
This study aimed to explore the connections between digital disorder, socio-demographics, physical health outcomes, and artificial intelligence (AI) on decision-making loss. The study relied on data from 550 people in Isfahan, Iran. The results showed that while decision-making loss was slightly more prevalent in females than males, this difference was not statistically significant. However, individuals aged between 26-35 showed a significant correlation with decision-making loss, while other age groups did not. Neither education level nor employment status demonstrated significant associations with decision-making loss, nor did the frequency of device use affect it either. Participants who experienced decision-making loss scored significantly higher on digital disorder overall score and specific indicators, such as addiction to social media and the internet, compared to those who did not. They also reported higher scores on various physical health outcomes related to device usage. © 2024, IGI Global. All rights reserved.
Publication Date: 2024
Multimodal Technologies and Interaction (24144088) 8(11)
Addressing human trafficking is crucial due to its severe impact on human rights, dignity, and well-being. Serious games refer to digital games that are designed to entertain while also accomplishing at least one additional objective, such as learning or health promotion. Serious games play a significant role in raising awareness, training professionals, fostering empathy, and advocating for policy improvements related to human trafficking. In this study, we systematically examine and assess the current landscape of serious games addressing human trafficking to unveil the existing state, pinpoint gaps, and propose future research avenues. Our investigation encompassed academic publications, gray literature, and commercial games related to human trafficking. Furthermore, we conducted a thorough review of evaluation criteria and heuristics for the comprehensive assessment of serious games. Subsequently, incorporating these evaluation metrics and heuristics, the games were subjected to evaluation by both players and experts. Following a combined qualitative and quantitative analysis, the results were deliberated upon, and their implications were expounded. Five serious games related to human trafficking were identified and evaluated using the SGES and EGameFlow scales, along with both game-specific and serious game heuristics. Player and expert evaluations ranked “(Un)TRAFFICKED” and “Missing” as the best-performing games, while “SAFE Travel” received the lowest ratings. Players generally rated the games higher than experts, particularly in usability, feedback, and goal clarity, although the games scored poorly in audiovisual quality and relevance. Experts highlighted deficiencies in motivation, challenge, and learning outcomes. The lack of personalization and the absence of social gaming elements point to the need for more targeted human trafficking games adapted to different demographics, cultures, and player types. © 2024 by the authors.
The swift expansion of the Internet of Things (IoT) has brought about a fundamental transformation in the functioning of enterprises, leading to the emergence of groundbreaking offerings in various industries. As this disruptive technology persists in reshaping sectors, comprehending the essential business models responsible for its prosperity becomes ever more essential. This investigation primarily aims to provide a thorough categorization of IoT business models with eight classes of business models, encompassing paradigms such as Product-oriented, Service-centric, Outcome-based, Pay-per-usage, Data-driven, Subscription, Compliance, and Testbed. Subsequently, challenges inherent to IoT business models are analyzed, accompanied by corresponding solutions. The study further provides an extensive overview and comparison of primary business model innovation (BMI) tools tailored to the IoT landscape, comparing those tools and investigating the primary features and usability of each BMI tool. © 2023 IEEE.
Publication Date: 2023
pp. 311-316
Today, leveraging analytical CRM to maximize values for both customers and businesses is one the most important critical success factors. Predicting customer loyalty enables businesses to differentiate among customers for conducting relationship marketing and implementing effective customer extension tactics. In this paper, we analyze customers' reviews on the Digikala e-marketplace to predict their loyalty. We employ NLP, deep learning, and conventional machine learning methods and evaluate the results to find the best prediction model. Two experiments are conducted to evaluate the results: binary and 3-class loyalty prediction. In the binary setting, the Random Forest and Naïve Bayes algorithms outperformed the other tested classification methods and achieved an accuracy of 89%. In the 3- class setting, the Random Forest classification method achieved the best performance among all other machine learning algorithms with an accuracy of 67%. The evaluation results imply that businesses could benefit from using the Random Forest classification algorithm to predict customer loyalty through review analysis successfully. © 2023 IEEE.
Publication Date: 2022
Education and Information Technologies (13602357) 27(6)pp. 8413-8460
In recent years, online learning has received more attention than ever before. One of the most challenging aspects of online education is the students' assessment since academic integrity could be violated due to various cheating behaviors in online examinations. Although a considerable number of literature reviews exist about online learning, there is no such review study to provide comprehensive insight into cheating motivations, cheating types, cheating detection, and cheating prevention in the online setting. The current study is a review of 58 publications about online cheating, published from January 2010 to February 2021. We present the categorization of the research and show topic trends in the field of online exam cheating. The study can be a valuable reference for educators and researchers working in the field of online learning to obtain a comprehensive view of cheating mitigation, detection, and prevention. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Publication Date: 2022
pp. 274-281
In the past few years, the number of private vehicles has risen intensely and will continue to grow in the future. Traffic management has become a significant concern as traffic issues directly affect the quality of life. Different methods have been implemented to track city traffic and find ways to reduce congestion, accidents, pollution, etc., but there is room for improvement. This study attempts to analyze Isfahan traffic through clustering traffic time series of intersections to find similar locations in the city. The result of this study would help traffic managers define appropriate policies and tactics for managing similar intersections effectively, which brings about time and cost saving for both citizens and the government. © 2022 IEEE.
Publication Date: 2022
pp. 65-72
Gathering and preparing high-quality data is one of the most significant and expensive steps in data analytics. Crowdsourcing is an efficient way to create datasets for machine learning and data science applications. However, it is vital to apply a proper crowdsourcing process for dataset creation to ensure the quality of the collected data. In this paper, a new process to create high-quality datasets based on crowdsourcing is proposed, including the pre-gathering, gathering, and post-gathering phases. Today employers and job seekers benefit from online job postings and social media sites for recruitment more than ever before. Consequently, a huge volume of job posting data is available that enforces the need for data visualization and data analytics for extracting valuable insights to help better decision making. Although there exist several online job advertisement datasets for analyzing job demand and requirements, there is no such dataset about the IT job market in Iran. In this paper, IranITJobs2021, an online IT job posting dataset, is presented, which is produced using the proposed dataset gathering process. IranITJobs2021 includes job advertisements related to information technology from August 2019 to January 2021. The dataset incorporates 1300 instances and 13 features which is publicly available. IranITJobs2021 could be analyzed to find valuable patterns of job requirements and skills in the field of information technology. Furthermore, the proposed dataset gathering process is applicable to create datasets efficiently. © 2022 IEEE.
Publication Date: 2021
User Modeling and User-Adapted Interaction (15731391) 31(2)pp. 225-259
Cultural dimensions are an important aspect of a user model and useful for many applications such as adapting user interface, managing marketing campaigns, customer relationship management, and human resource management. Traditionally, these dimensions are measured through CVSCALE, which is a reliable and standard scale provided to measure Hofstede’s cultural dimensions at the individual level. The problems with the questionnaire-based data collection are low response rates, lack of willingness to complete, poor engagement of participants, and concern about the quality of data collected. To solve these problems, we present a serious video game called “Treasure Island” to measure the cultural dimensions of the player at the individual level (currently only for the Persian language). We have developed and validated a Persian-language version of CVSCALE applied to design the game. We developed the very first general game development process to build serious games for gathering the same data as a standard psychometric questionnaire. Treasure Island has been evaluated by statistical analysis of the data collected from a sample of 285 participants that have played the game and completed the questionnaire. The results indicate that Treasure Island is effective to measure the individual cultural dimensions. Moreover, the efficiency of the game has been tested in terms of task load imposed on the user during playing the game and completing the questionnaire. The results demonstrate that the game imposes less task load on the user, consequently, improves user satisfaction and engagement. Since individual cultural dimensions can be considered an important facet of a user model for certain applications, the proposed serious game can be applied for user modeling and personalization purposes. © 2020, Springer Nature B.V.
Publication Date: 2020
pp. 24-29
Today, ransomware is one of the most harmful cybersecurity threats that organizations and people face. Hence, there is a vital need for developing effective ransomware detection methods. Machine learning methods can be very useful for ransomware detection if there is sufficient labeled data for training. However, labeling data is time-consuming and expensive while a huge amount of unlabeled data exists. To cope with this problem, semi-supervised learning can be employed that exploits a few labeled data and a lot of unlabeled data for learning. To our best knowledge, there is no research investigating semi-supervised learning methods for ransomware detection. In this paper, we analyze different feature selection and semi-supervised classification methods applied to the CICAndMal 2017 dataset. Our findings suggest that the wrapper semi-supervised classification method using the random forest as a base classifier and OneR or Chi-squared as a feature selection method outperforms the other semi-supervised classification methods for ransomware detection. © 2020 IEEE.
Publication Date: 2019
Journal of Research in Interactive Marketing (2040-7122) 13(3)pp. 392-410
Purpose: Today, marketing has evolved due to the emergence of new electronic technologies and has shifted to e-marketing. Meanwhile, the gamification and gamified systems is an up-to-date research topic that has attracted the attention of many researchers in recent years. As one of the main goals of marketing is to increase customer engagement and loyalty by persuading and motivating them to participate, the gamification has a great potential for e-marketing. Although much research has been done on the gamification subject in e-marketing, there has not yet been a comprehensive review of these studies. This paper aims to provide a comprehensive overview of the scientific and practical research on gamification applied to e-marketing using the systematic mapping study methodology. Design/methodology/approach: Because considerable research has been devoted to gamification since 2011, and the number of papers published in this area has grown steadily from 2011, the paper reviews the publications over the period 2011-2018. The research method includes developing research questions, designing the research process and filtering the findings based on the specified criteria. Findings: The findings of this study show the main applications of gamification in e-marketing, the technologies used and the proven benefits of applying this technique in e-marketing. It also provides a classification of the studies in this area. Practical implications: This paper helps other researchers to understand the main areas of research in gamification within the marketing discipline and enables them to find the fields needed for future studies. Originality/value: The proposed classification can give a comprehensive overview of the scientific and practical actions taken on gamification applied to e-marketing for academics and practitioners. It also enables the readers to find main areas of research and motivates them to apply gamification in e-marketing. © 2019, Emerald Publishing Limited.
Publication Date: 2019
pp. 128-133
In parallel with the increasing growth of the Internet and computer networks, the number of malwares has been increasing every day. Today, one of the newest attacks and the biggest threats in cybersecurity is ransomware. The effectiveness of applying machine learning techniques for malware detection has been explored in much scientific research, however, there is few studies focused on machine learning-based ransomware detection. In this paper, the effectiveness of ransomware detection using machine learning methods applied to CICAndMal2017 dataset is examined in two experiments. First, the classifiers are trained on a single dataset containing different types of ransomware. Second, different classifiers are trained on datasets of 10 ransomware families distinctly. Our findings imply that in both experiments random forest outperforms other tested classifiers and the performance of the classifiers are not changed significantly when they are trained on each family distinctly. Therefore, the random forest classification method is very effective in ransomware detection. © 2019 IEEE.
Publication Date: 2018
pp. 120-125
Network traffic classification is an essential requirement for network management. Various approaches have been developed for network traffic classification. Traditional approaches such as analysis of port number or payload have some limitations. For example, using port numbers for traffic classification fails if an application uses dynamic port number or applies encryption methods. To address such limitations, modern traffic classification methods employ machine learning techniques. However, machine learning-based traffic classification needs a large labeled data to extract accurate classification model which is expensive and time-consuming. To overcome this issue, we propose a new semi-supervised method for traffic classification based on x-means clustering algorithm and a new label propagation technique. The accuracy of the proposed method tested on Moore's dataset is 0.95 that shows its effectiveness for learning a network traffic classifier using a limited labeled data. © 2018 IEEE.
Publication Date: 2018
pp. 104-109
A recommender system is an information filtering tool that copes with the growing volume of information and helps the user to make faster decisions by providing products and services matched with their needs and interests. However, a large number of users are not satisfied with the provided recommendations and do not accept them. Based on the Elaboration Likelihood Model (ELM), If supplementary information about recommendations is provided, those users having the low motivation and capability to analyze the usefulness of the recommended item can be persuaded to accept it. This paper focuses on analyzing the impact of demographic factors on increasing the acceptance of recommendations. This study was conducted by a web-based online survey. The movie's recommender system has been developed along with the explanations based on Cialdini's persuasion strategies as the peripheral cues. The collected data are analyzed through statistical techniques using the SPSS software. The results show that the persuasiveness degree of the persuasion strategies differs related to individuals with the different demographic factors. © 2018 IEEE.
Publication Date: 2017
2018pp. 165-171
The employee's performance evaluation in organizations is one of the major challenges of the management that has been received a great attention by researchers and managers. The main problem of the current performance evaluation methods is the impact of individual emotions and employee judgments on the evaluation process, which reduces results in the biased evaluation. To solve this problem, in this paper a new method based on Fuzzy AHP and fuzzy TOPSIS for employee performance evaluation are presented. First, the weight of the evaluation criteria is calculated using the Fuzzy AHP method. Next, each employee's performance is scored by weighted criteria using Fuzzy TOPSIS method. The proposed method has been tested on employees of the Entekhab Industrial Group. The results indicate that the proposed method is more effective than other evaluation methods in employee performance evaluation. © 2017 IEEE.
Publication Date: 2017
Pattern Analysis and Applications (1433755X) 20(3)pp. 701-715
Supervised clustering is a new research area that aims to improve unsupervised clustering algorithms exploiting supervised information. Today, there are several clustering algorithms, but the effective supervised cluster adjustment method which is able to adjust the resulting clusters, regardless of applied clustering algorithm has not been presented yet. In this paper, we propose a new supervised cluster adjustment method which can be applied to any clustering algorithm. Since the adjustment method is based on finding the nearest neighbors, a novel exact nearest neighbor search algorithm is also introduced which is significantly faster than the classic one. Several datasets and clustering evaluation metrics are employed to examine the effectiveness of the proposed cluster adjustment method and the proposed fast exact nearest neighbor algorithm comprehensively. The experimental results show that the proposed algorithms are significantly effective in improving clusters and accelerating nearest neighbor searches. © 2015, Springer-Verlag London.
Publication Date: 2017
International Journal of Communication Systems (10991131) 30(4)
In recent years, the utilization of machine learning and data mining techniques for intrusion detection has received great attention by both security research communities and intrusion detection system (IDS) developers. In intrusion detection, the most important constraints are the imbalanced class distribution, the scarcity of the labeled data, and the massive amounts of network flows. Moreover, because of the dynamic nature of the network flows, applying static learned models degrades the detection performance significantly over time. In this article, we propose a new semi-supervised stream classification method for intrusion detection, which is capable of incremental updating using limited labeled data. The proposed method, called the incremental semi-supervised flow network-based IDS (ISF-NIDS), relies on an incremental mixed-data clustering, a new supervised cluster adjustment method, and an instance-based learning. The ISF-NIDS operates in real time and learns new intrusions quickly using limited storage and processing power. The experimental results on the KDD99, Moore, and Sperotto benchmark datasets indicate the superiority of the proposed method compared with the existing state-of-the-art incremental IDSs. Copyright © 2015 John Wiley & Sons, Ltd.
Publication Date: 2017
pp. 148-156
Despite the increasing use of internet by Iranians, the bounce rates of the e-commerce websites are still high. This is because the e-commerce institutions are not familiar with designing websites based on their own target market preferences. So the purpose of this paper is to identify and to evaluate the effective visual factors for attracting online users. This study has been conducted by an attitude assessment through an online user questionnaire to collect demographic data that influence the user's color preferences and interests. Next, statistical analysis was done through a variety of tests including T-Test, ANOVA-Test and Duncan-Test. These tests are employed to find the relationship between user's demographic features and his/her preferred color on websites. The results of this study can be useful to personalize the websites exploiting the extracted rules of colors. © 2017 IEEE.
Publication Date: 2017
pp. 178-184
With the proliferation of the internet and increased global access to online media, cybercrime is also occurring at an increasing rate. Currently, both personal users and companies are vulnerable to cybercrime. A number of tools including firewalls and Intrusion Detection Systems (IDS) can be used as defense mechanisms. A firewall acts as a checkpoint which allows packets to pass through according to predetermined conditions. In extreme cases, it may even disconnect all network traffic. An IDS, on the other hand, automates the monitoring process in computer networks. The streaming nature of data in computer networks poses a significant challenge in building IDS. In this paper, a method is proposed to overcome this problem by performing online classification on datasets. In doing so, an incremental naive Bayesian classifier is employed. Furthermore, active learning enables solving the problem using a small set of labeled data points which are often very expensive to acquire. The proposed method includes two groups of actions i.e. offline and online. The former involves data preprocessing while the latter introduces the NADAL online method. The proposed method is compared to the incremental naive Bayesian classifier using the NSL-KDD standard dataset. There are three advantages with the proposed method: (1) overcoming the streaming data challenge; (2) reducing the high cost associated with instance labeling; and (3) improved accuracy and Kappa compared to the incremental naive Bayesian approach. Thus, the method is well-suited to IDS applications. © 2017 IEEE.
Publication Date: 2015
Soft Computing (14327643) 19(3)pp. 731-743
Clustering is one of the most applied unsupervised machine learning tasks. Although there exist several clustering algorithms for numeric data, more sophisticated clustering algorithms to address mixed data (numeric and categorical data) more efficiently are still required. Other important issues to be considered in clustering are incremental learning and generating a sufficient number of clusters without specifying the number of clusters a priori. In this paper, we introduce a mixed data clustering method which is incremental and generates a sufficient number of clusters automatically. The proposed method is based on the Adjusted Self-Organizing Incremental Neural Network (ASOINN) algorithm exploiting a new distance measure and new update rules for handling mixed data. The proposed clustering method is compared with the ASOINN and three other clustering algorithms comprehensively. The results of comparative experiments on various data sets using several clustering evaluation measures show the effectiveness of the proposed mixed data clustering method. © 2014, Springer-Verlag Berlin Heidelberg.
Publication Date: 2013
Educational Technology And Society (11763647) 16(3)pp. 88-101
Assessment is one of the most essential parts of any instructive learning process which aims to evaluate a learner's knowledge about learning concepts. In this work, a new method for learner assessment based on learner annotations is presented. The proposed method exploits the M-BLEU algorithm to find the most similar reference annotations and then the learner annotation will be processed further to check essential words, words order and contradictions. To examine this new approach, a virtual learning environment was designed and implemented in which assessment of the learner's knowledge is performed on the basis of main and sub concepts. These concepts are delivered by means of course contents and the learning environment guides the user to annotate concepts. Evaluation results show that our designed system can effectively assess learner's knowledge. The benefit of suggested assessment method is its implicitness of assessment approach. Furthermore the correct annotations can be used to help the users remembering concepts by reviewing their annotations. © International Forum of Educational Technology & Society (IFETS).
Publication Date: 2011
Computers and Education (0360-1315) 56(2)pp. 337-345
e-Learning plays an undoubtedly important role in today's education and assessment is one of the most essential parts of any instruction-based learning process. Assessment is a common way to evaluate a student's knowledge regarding the concepts related to learning objectives. In this paper, a new method for assessing the free text answers of students based on the BLEU algorithm is presented. We modify the BLEU algorithm so that it is suitable for assessing free text answers and call the new algorithm the modified BLEU (M-BLEU). To perform an assessment, it is necessary to establish a repository of reference answers written by course instructors or related experts. Several reference answers are included for each question. The M-BLEU algorithm is used to identify the most similar reference answer to a student answer; a similarity score is calculated and applied to score the answers provided by students. Evaluation results show that the proposed method achieves the highest correlation with human expert scores compared to other assessment methods such as latent semantic analysis (LSA) and n-gram co-occurrence. © 2010 Elsevier Ltd. All rights reserved.
Publication Date: 2009
Proceedings of the International Conference on e-Learning, ICEL (20488882) 2009pp. 386-393
Nowadays e-learning has an important role in learning and education. There is no doubt in importance of personalized and adaptive learning. In this field there are many adaptation methods such as adaptive presentation and navigation methods. The idea of various adaptive presentation techniques is to adapt the content of a page accessed by a particular user to current knowledge, interests, and other characteristics of the user. In this paper we present a new method for content adaptation: Personalized Summary Generation. We consider user knowledge and interests to generate personalized summary for text-based courses in e-learning systems. If we can generate personalized summaries it can increase learning speed and improve learning process. Personalized summaries reduce the volume of irrelevance learning content. Our summarization method generates summary regarding to user knowledge and interests through four phases: Preprocessing, Initial scoring, scoring based on interest & knowledge and Personalized summary generation. We will test our proposed method and show experimental results. Copyright The Authors, 2009. All Rights Reserved.
Publication Date: 2009
pp. 1128-1133
Nowadays e-learning has an important role in learning and education. Obviously one of the most important challenges in e-learning is to produce appropriate learning contents for learners. One solution might be using annotations of learners to select and edit learning contents. Due to the possibility of adding annotations to a specific learning content, exploiting learners' annotations can help author to improve learning content. Regarding to concepts' ontology and contents' annotations, it is possible to edit certain content in contents hierarchy. In addition it is possible to create learning contents by selecting high rated learners' annotations and presenting them to new learners. The benefits of the method using annotations for editing contents, is that it is implicit and having each annotation the related content can be found and if necessary it can be edited or improved . In this paper we try to present a framework for using learners' annotations in order to selecting and editing learning contents in e-learning systems. We describe details of annotations classification and method of rating annotations. In addition, the proposed solution has been tested and benefits of annotations analyze to produce feedbacks for authors have been shown. © 2009 IEEE.
Address Isfahan, Azadi Square, University of Isfahan
