Defending recommender systems by influence analysis

Collaborative filtering (CF) is a popular method for personalizing product recommendations for e-commerce applications. In order to recommend a product to a user and predict that user’s preference, CF utilizes product evaluation ratings of like-minded users. The process of finding like-minded users forms a social network among all users and each link between two users represents an implicit connection between them. Users having more connections with others are the most influential users. Attacking recommender systems is a new issue for these systems. Here, an attacker tries to manipulate a recommender system in order to change the recommendation output according to her wish. If an attacker succeeds, her profile is used over and over again by the recommender system, making her an influential user. In this study, we applied the established attack detection methods to the influential users, instead of the whole user set, to improve their attack detection performance. Experiments were conducted using the same settings previously used to test the established methods. The results showed that the proposed influence-based method had better detection performance and improved the stability of a recommender system for most attack scenarios. It performed considerably better than established detection methods for attacks that inserted low numbers of attack profiles (20–25 %).     

An exploration of EFL teachers’ attributions

The present study investigated English as a foreign language (EFL) teachers’ attributions of success and failure. It also set out to investigate whether these attributions vary by teachers’ age, teaching experience, gender and educational level. To do so, 200 EFL teachers were selected according to convenience sampling among EFL teachers teaching English in Language Institutes in Mashhad and Tehran, two cities in Iran. The participants completed the language teacher attribution scale measuring four attributions: teaching competency (TC), teacher effort (TE), student effort (SE) and institution supervision (IS). The present study yielded mixed results regarding English language teachers’ attributions of success and failure events. It was also found that these attributions vary by their age, teaching experience and educational level, but not by gender. The discussion and implications of the research are further presented with reference to the earlier findings.     

A novel controller for nonlinear uncertain systems using a combination of SDRE and function approximation technique: Regulation and tracking of flexible-joint manipulators

This paper presents a novel combined State Dependent Riccati Equation (SDRE) / Function Approximation Technique (FAT)-based control design for nonlinear uncertain systems. The SDRE is employed to construct an optimal controller and the function approximation technique is utilized to estimate time-varying disturbances and uncertainties. Moreover, a robust term in the proposed control law compensates for the truncation error. The closed-loop stability and boundedness of the tracking error and FAT weights approximation error are proved in the sense of Lyapunov, with consideration of truncation error. Due to the great importance of the adequate performance of transient response from practical point of view, performance evaluation has been accomplished. The proposed scheme is computationally simple due to utilizing the FAT to represent uncertainties and disturbances as a function of time. Compared with the SDRE based SMC, the proposed controller is superior in terms of capability to track a fast and highly complicated trajectory and no need to determine time-varying disturbances and uncertainties bounds. The case study is a Selective Compliant Articulated Robot for Assembly (SCARA) flexible joint manipulator as a representative of highly nonlinear, coupled, large robotic systems. Simulation results easily verify the effectiveness and superiority of the proposed controller.     

Trait emotional intelligence and learning styles: the case of Iranian English for Academic Purposes learners

Although a large body of research has been dedicated to examining emotional intelligence (EI) and learning styles in relation to different factors in academic setting, the relationship between these two variables still necessitates more exploration and deeper study, especially in the Iranian context. To this end, 60 English for Academic Purposes (EAP) learners were recruited to fill out the Farsi version of Emotional Intelligence Scale (FEIS-41) and Paragon Learning Styles Inventory (PLSI). The results revealed that the participants achieved the highest score in Optimism/Mood Regulation sub-scale of the FEIS-41. With respect to the four dimensions of PLSI, Sensing, Feeling, Judging and Extrovert were the participants’ preferred learning styles, respectively. Besides, analysis of data illustrated that gender did not affect their EI and learning styles preferences. Furthermore, the significance of 9 out of 12 computed correlations between three sub-skills of FEIS-41 and four dimensions of PLSI indicated the existence of correlation between EI and learning styles preferences of Iranian EAP learners.     

A review of empirical studies of social media on language learners’ willingness to communicate

Education and Information Technologies - Many studies have explored educational and pedagogical affordances of social media, but few studies have investigated their impact on emotional and...     

Understanding privacy and data protection issues in learning analytics using a systematic review

The field of learning analytics has advanced from infancy stages into a more practical domain, where tangible solutions are being implemented. Nevertheless, the field has encountered numerous privacy and data protection issues that have garnered significant and growing attention. In this systematic review, four databases were searched concerning privacy and data protection issues of learning analytics. A final corpus of 47 papers published in top educational technology journals was selected after running an eligibility check. An analysis of the final corpus was carried out to answer the following three research questions: (1) What are the privacy and data protection issues in learning analytics? (2) What are the similarities and differences between the views of stakeholders from different backgrounds on privacy and data protection issues in learning analytics? (3) How have previous approaches attempted to address privacy and data protection issues? The results of the systematic review show that there are eight distinct, intertwined privacy and data protection issues that cut across the learning analytics cycle. There are both cross-regional similarities and three sets of differences in stakeholder perceptions towards privacy and data protection in learning analytics. With regard to previous attempts to approach privacy and data protection issues in learning analytics, there is a notable dearth of applied evidence, which impedes the assessment of their effectiveness. The findings of our paper suggest that privacy and data protection issues should not be relaxed at any point in the implementation of learning analytics, as these issues persist throughout the learning analytics development cycle. One key implication of this review suggests that solutions to privacy and data protection issues in learning analytics should be more evidence-based, thereby increasing the trustworthiness of learning analytics and its usefulness.

Practitioner notes

What is already known about this topic

• Research on privacy and data protection in learning analytics has become a recognised challenge that hinders the further expansion of learning analytics.
• Proposals to counter the privacy and data protection issues in learning analytics are blurry; there is a lack of a summary of previously proposed solutions.

What this study contributes

• Establishment of what privacy and data protection issues exist at different phases of the learning analytics cycle.
• Identification of how different stakeholders view privacy, similarities and differences, and what factors influence their views.
• Evaluation and comparison of previously proposed solutions that attempt to address privacy and data protection in learning analytics.

Implications for practice and/or policy

• Privacy and data protection issues need to be viewed in the context of the entire cycle of learning analytics.
• Stakeholder views on privacy and data protection in learning analytics have commonalities across contexts and differences that can arise within the same context. Before implementing learning analytics, targeted research should be conducted with stakeholders.
• Solutions that attempt to address privacy and data protection issues in learning analytics should be put into practice as far as possible to better test their usefulness.