A comprehensive overview of biometric fusion

With an unprecedented scale of learners watching educational videos on online platforms such as MOOCs and YouTube, there is an opportunity to incorporate data generated from their interactions into the design of novel video interaction techniques. Interaction data has the potential to help not only instructors to improve their videos, but also to enrich the learning experience of educational video watchers. This paper explores the design space of data-driven interaction techniques for educational video navigation. We introduce a set of techniques that augment existing video interface widgets, including: a 2D video timeline with an embedded visualization of collective navigation traces; dynamic and non-linear timeline scrubbing; data-enhanced transcript search and keyword summary; automatic display of relevant still frames next to the video; and a visual summary representing points with high learner activity. To evaluate the feasibility of the techniques, we ran a laboratory user study with simulated learning tasks. Participants rated watching lecture videos with interaction data to be efficient and useful in completing the tasks. However, no significant differences were found in task performance, suggesting that interaction data may not always align with moment-by-moment information needs during the tasks.

Data-driven interaction techniques for improving navigation of educational videos

With advanced digitalisation, we can observe a massive increase of user-generated content on the web that provides opinions of people on different subjects. Sentiment analysis is the computational study of analysing people's feelings and opinions for an entity. The field of sentiment analysis has been the topic of extensive research in the past decades. In this paper, we present the results of a tertiary study, which aims to investigate the current state of the research in this field by synthesizing the results of published secondary studies (i.e., systematic literature review and systematic mapping study) on sentiment analysis. This tertiary study follows the guidelines of systematic literature reviews (SLR) and covers only secondary studies. The outcome of this tertiary study provides a comprehensive overview of the key topics and the different approaches for a variety of tasks in sentiment analysis. Different features, algorithms, and datasets used in sentiment analysis models are mapped. Challenges and open problems are identified that can help to identify points that require research efforts in sentiment analysis. In addition to the tertiary study, we also identified recent 112 deep learning-based sentiment analysis papers and categorized them based on the applied deep learning algorithms. According to this analysis, LSTM and CNN algorithms are the most used deep learning algorithms for sentiment analysis.

/pdf/systematic-reviews-in-sentiment-analysis-a-tertiary-study-40dbx65681.pdf

Systematic reviews in sentiment analysis: a tertiary study

Students’ feedback is an effective mechanism that provides valuable insights about teaching-learning process. Handling opinions of students expressed in reviews is a quite labour-intensive and tedious task as it is typically performed manually by the human intervention. While this task may be viable for small-scale courses that involve just a few students’ feedback, it is unpractical for large-scale cases as it applies to online courses in general, and MOOCs, in particular. Therefore, to address this issue, we propose in this paper a framework to automatically analyzing opinions of students expressed in reviews. Specifically, the framework relies on aspect-level sentiment analysis and aims to automatically identify sentiment or opinion polarity expressed towards a given aspect related to the MOOC. The proposed framework takes advantage of weakly supervised annotation of MOOC-related aspects and propagates the weak supervision signal to effectively identify the aspect categories discussed in the unlabeled students’ reviews. Consequently, it significantly reduces the need for manually annotated data which is the main bottleneck for all deep learning techniques. A large-scale real-world education dataset containing around 105k students’ reviews collected from Coursera and a dataset comprising of 5989 students’ feedback in traditional classroom settings are used to perform experiments. The experimental results indicate that our proposed framework attains inspiring performance with respect to both the aspect category identification and the aspect sentiment classification. Moreover, the results suggest that the framework leads to more accurate results than the expensive and labour-intensive sentiment analysis techniques relying heavily on manually labelled data.

/pdf/weakly-supervised-framework-for-aspect-based-sentiment-3y9jes8glk.pdf

Weakly Supervised Framework for Aspect-Based Sentiment Analysis on Students’ Reviews of MOOCs

Smartphones have become crucial for our daily life activities and are increasingly loaded with our personal information to perform several sensitive tasks, including, mobile banking and communication, and are used for storing private photos and files. Therefore, there is a high demand for applying usable authentication techniques that prevent unauthorized access to sensitive information. In this article, we propose AUTo Sen , a deep-learning-based active authentication approach that exploits sensors in consumer-grade smartphones to authenticate a user. Unlike conventional approaches, AUTo Sen is based on deep learning to identify user distinct behavior from the embedded sensors with and without the user’s interaction with the smartphone. We investigate different deep learning architectures in modeling and capturing users’ behavioral patterns for the purpose of authentication. Moreover, we explore the sufficiency of sensory data required to accurately authenticate users. We evaluate AUTo Sen on a real-world data set that includes sensors data of 84 participants’ smartphones collected using our designed data-collection application. The experiments show that AUTo Sen operates accurately using readings of only three sensors (accelerometer, gyroscope, and magnetometer) with a high authentication frequency, e.g., one authentication attempt every 0.5 s. Using sensory data of one second enables an authentication F1-score of approximately 98%, false acceptance rate (FAR) of 0.95%, false rejection rate (FRR) of 6.67%, and equal error rate (EER) of 0.41%. While using sensory data of half a second enables an authentication F1-score of 97.52%, FAR of 0.96%, FRR of 8.08%, and EER of 0.09%. Moreover, we investigate the effects of using different sensory data at variable sampling periods on the performance of the authentication models under various settings and learning architectures.

AUTo Sen : Deep-Learning-Based Implicit Continuous Authentication Using Smartphone Sensors

Recommender systems learn from historical users’ feedback that is often non-uniformly distributed across items. As a consequence, these systems may end up suggesting popular items more than niche items progressively, even when the latter would be of interest for users. This can hamper several core qualities of the recommended lists (e.g., novelty, coverage, diversity), impacting on the future success of the underlying platform itself. In this paper, we formalize two novel metrics that quantify how much a recommender system equally treats items along the popularity tail. The first one encourages equal probability of being recommended across items, while the second one encourages true positive rates for items to be equal. We characterize the recommendations of representative algorithms by means of the proposed metrics, and we show that the item probability of being recommended and the item true positive rate are biased against the item popularity. To promote a more equal treatment of items along the popularity tail, we propose an in-processing approach aimed at minimizing the biased correlation between user-item relevance and item popularity. Extensive experiments show that, with small losses in accuracy, our popularity-mitigation approach leads to important gains in beyond-accuracy recommendation quality.

Connecting user and item perspectives in popularity debiasing for collaborative recommendation

Bridging learning analytics and Cognitive Computing for Big Data classification in micro-learning video collections

A multi-biometric system for continuous student authentication in e-learning platforms

Most recommender systems are evaluated on how they accurately predict user ratings. However, individuals use them for more than an anticipation of their preferences. The literature demonstrated that some recommendation algorithms achieve good prediction accuracy, but suffer from popularity bias. Other algorithms generate an item category bias due to unbalanced rating distributions across categories. These effects have been widely analyzed in the context of books, movies, music, and tourism, but contrasting conclusions have been reached so far. In this paper, we explore how recommender systems work in the context of massive open online courses, going beyond prediction accuracy. To this end, we compared existing algorithms and their recommended lists against biases related to course popularity, catalog coverage, and course category popularity. Our study remarks even more the need of better understanding how recommenders react against bias in diverse contexts.

The Effect of Algorithmic Bias on Recommender Systems for Massive Open Online Courses

With the proliferation in number and scale of online courses, several challenges have emerged in supporting stakeholders during their delivery and fruition. Machine Learning and Semantic Analysis can add value to the underlying online environments in order to overcome a subset of such challenges (e.g. classification, retrieval, and recommendation). However, conducting reproducible experiments in these applications is still an open problem due to the lack of available datasets in Technology-Enhanced Learning (TEL), mostly small and local. In this paper, we propose COCO, a novel semantic-enriched collection including over 43 K online courses at scale, 16 K instructors and 2,5 M learners who provided 4,5 M ratings and 1,2 M comments in total. This outruns existing TEL datasets in terms of scale, completeness, and comprehensiveness. Besides describing the collection procedure and the dataset structure, we depict and analyze two potential use cases as meaningful examples of the large variety of multi-disciplinary studies made possible by having COCO.

Mirko Marras

Papers

Connecting user and item perspectives in popularity debiasing for collaborative recommendation

Bridging learning analytics and Cognitive Computing for Big Data classification in micro-learning video collections

A multi-biometric system for continuous student authentication in e-learning platforms

The Effect of Algorithmic Bias on Recommender Systems for Massive Open Online Courses

COCO: Semantic-Enriched Collection of Online Courses at Scale with Experimental Use Cases