| 1. |
- Afzaal, Muhammad, et al.
(författare)
-
Explainable AI for Data-Driven Feedback and Intelligent Action Recommendations to Support Students Self-Regulation
- 2021
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media SA. - 2624-8212. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- Formative feedback has long been recognised as an effective tool for student learning, and researchers have investigated the subject for decades. However, the actual implementation of formative feedback practices is associated with significant challenges because it is highly time-consuming for teachers to analyse students’ behaviours and to formulate and deliver effective feedback and action recommendations to support students’ regulation of learning. This paper proposes a novel approach that employs learning analytics techniques combined with explainable machine learning to provide automatic and intelligent feedback and action recommendations that support student’s self-regulation in a data-driven manner, aiming to improve their performance in courses. Prior studies within the field of learning analytics have predicted students’ performance and have used the prediction status as feedback without explaining the reasons behind the prediction. Our proposed method, which has been developed based on LMS data from a university course, extends this approach by explaining the root causes of the predictions and by automatically providing data-driven intelligent recommendations for action. Based on the proposed explainable machine learning-based approach, a dashboard that provides data-driven feedback and intelligent course action recommendations to students is developed, tested and evaluated. Based on such an evaluation, we identify and discuss the utility and limitations of the developed dashboard. According to the findings of the conducted evaluation, the dashboard improved students’ learning outcomes, assisted them in self-regulation and had a positive effect on their motivation.
|
|
| 2. |
- Dalipi, Fisnik, Senior lecturer, et al.
(författare)
-
Sentiment Analysis of Students’ Feedback in MOOCs : A Systematic Literature Review
- 2021
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 4
-
Forskningsöversikt (refereegranskat)abstract
- In recent years, sentiment analysis (SA) has gained popularity among researchers in various domains, including the education domain. Particularly, sentiment analysis can be applied to review the course comments in massive open online courses (MOOCs), which could enable instructors to easily evaluate their courses. This article is a systematic literature review on the use of sentiment analysis for evaluating students’ feedback in MOOCs, exploring works published between January 1, 2015, and March 4, 2021. To the best of our knowledge, this systematic review is the first of its kind. We have applied a stepwise PRISMA framework to guide our search process, by searching for studies in six electronic research databases (ACM, IEEE, ScienceDirect, Springer, Scopus, and Web of Science). Our review identified 40 relevant articles out of 440 that were initially found at the first stage. From the reviewed literature, we found that the research has revolved around six areas: MOOC content evaluation, feedback contradiction detection, SA effectiveness, SA through social network posts, understanding course performance and dropouts, and MOOC design model evaluation. In the end, some recommendations are provided and areas for future research directions are identified.
|
|
| 3. |
- Ilinykh, Nikolai, 1994, et al.
(författare)
-
What Does a Language-And-Vision Transformer See: The Impact of Semantic Information on Visual Representations
- 2021
-
Ingår i: Frontiers in Artificial Intelligence: Identifying, Analyzing, and Overcoming Challenges in Vision and Language Research. - : Frontiers Media SA. - 2624-8212. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- Neural networks have proven to be very successful in automatically capturing the composition of language and different structures across a range of multi-modal tasks. Thus, an important question to investigate is how neural networks learn and organise such structures. Numerous studies have examined the knowledge captured by language models (LSTMs, transformers) and vision architectures (CNNs, vision transformers) for respective uni-modal tasks. However, very few have explored what structures are acquired by multi-modal transformers where linguistic and visual features are combined. It is critical to understand the representations learned by each modality, their respective interplay, and the task’s effect on these representations in large-scale architectures. In this paper, we take a multi-modal transformer trained for image captioning and examine the structure of the self-attention patterns extracted from the visual stream. Our results indicate that the information about different relations between objects in the visual stream is hierarchical and varies from local to a global object-level understanding of the image. In particular, while visual representations in the first layers encode the knowledge of relations between semantically similar object detections, often constituting neighbouring objects, deeper layers expand their attention across more distant objects and learn global relations between them. We also show that globally attended objects in deeper layers can be linked with entities described in image descriptions, indicating a critical finding - the indirect effect of language on visual representations. In addition, we highlight how object-based input representations affect the structure of learned visual knowledge and guide the model towards more accurate image descriptions. A parallel question that we investigate is whether the insights from cognitive science echo the structure of representations that the current neural architecture learns. The proposed analysis of the inner workings of multi-modal transformers can be used to better understand and improve on such problems as pre-training of large-scale multi-modal architectures, multi-modal information fusion and probing of attention weights. In general, we contribute to the explainable multi-modal natural language processing and currently shallow understanding of how the input representations and the structure of the multi-modal transformer affect visual representations.
|
|
| 4. |
- Lukmanov, Rustam A., et al.
(författare)
-
On Topological Analysis of fs-LIMS Data. Implications for in Situ Planetary Mass Spectrometry
- 2021
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- In this contribution, we present results of non-linear dimensionality reduction and classification of the fs laser ablation ionization mass spectrometry (LIMS) imaging dataset acquired from the Precambrian Gunflint chert (1.88 Ga) using a miniature time-of-flight mass spectrometer developed for in situ space applications. We discuss the data generation, processing, and analysis pipeline for the classification of the recorded fs-LIMS mass spectra. Further, we define topological biosignatures identified for Precambrian Gunflint microfossils by projecting the recorded fs-LIMS intensity space into low dimensions. Two distinct subtypes of microfossil-related spectra, a layer of organic contamination and inorganic quartz matrix were identified using the fs-LIMS data. The topological analysis applied to the fs-LIMS data allows to gain additional knowledge from large datasets, formulate hypotheses and quickly generate insights from spectral data. Our contribution illustrates the utility of applying spatially resolved mass spectrometry in combination with topology-based analytics in detecting signatures of early (primitive) life. Our results indicate that fs-LIMS, in combination with topological methods, provides a powerful analytical framework and could be applied to the study of other complex mineralogical samples.
|
|
| 5. |
- Lundberg, Jonas, 1974-, et al.
(författare)
-
Human Autonomy in Future Drone Traffic : Joint Human-AI Control in Temporal Cognitive Work
- 2021
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- The roles of human operators are changing due to increased intelligence and autonomy of computer systems. Humans will interact with systems at a more overarching level or only in specific situations. This involves learning new practices and changing habitual ways of thinking and acting, including reconsidering human autonomy in relation to autonomous systems. This paper describes a design case of a future autonomous management system for drone traffic in cities in a key scenario we call The Computer in Brussels. Our approach to designing for human collaboration with autonomous systems builds on scenario-based design and cognitive work analysis facilitated by computer simulations. We use a temporal method, called the Joint Control Framework to describe human and automated work in an abstraction hierarchy labeled Levels of Autonomy in Cognitive Control. We use the Score notation to analyze patterns of temporal developments that span levels of the abstraction hierarchy and discuss implications for human-automation communication in traffic management. We discuss how autonomy at a lower level can prevent autonomy on higher levels, and vice versa. We also discuss the temporal nature of autonomy in minute-to-minute operative work. Our conclusion is that human autonomy in relation to autonomous systems is based on fundamental trade-offs between technological opportunities to automate and values of what human actors find meaningful.
|
|
| 6. |
- Methnani, Leila, et al.
(författare)
-
Let Me Take Over : Variable Autonomy for Meaningful Human Control
- 2021
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- As Artificial Intelligence (AI) continues to expand its reach, the demand for human control and the development of AI systems that adhere to our legal, ethical, and social values also grows. Many (international and national) institutions have taken steps in this direction and published guidelines for the development and deployment of responsible AI systems. These guidelines, however, rely heavily on high-level statements that provide no clear criteria for system assessment, making the effective control over systems a challenge. “Human oversight” is one of the requirements being put forward as a means to support human autonomy and agency. In this paper, we argue that human presence alone does not meet this requirement and that such a misconception may limit the use of automation where it can otherwise provide so much benefit across industries. We therefore propose the development of systems with variable autonomy—dynamically adjustable levels of autonomy—as a means of ensuring meaningful human control over an artefact by satisfying all three core values commonly advocated in ethical guidelines: accountability, responsibility, and transparency.
|
|
| 7. |
- Sahlgren, Magnus, et al.
(författare)
-
The Singleton Fallacy : Why Current Critiques of Language Models Miss the Point
- 2021
-
Ingår i: Frontiers in Artificial Intelligence. - : Frontiers Media S.A.. - 2624-8212. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- This paper discusses the current critique against neural network-based Natural Language Understanding solutions known as language models. We argue that much of the current debate revolves around an argumentation error that we refer to as the singleton fallacy: the assumption that a concept (in this case, language, meaning, and understanding) refers to a single and uniform phenomenon, which in the current debate is assumed to be unobtainable by (current) language models. By contrast, we argue that positing some form of (mental) “unobtanium” as definiens for understanding inevitably leads to a dualistic position, and that such a position is precisely the original motivation for developing distributional methods in computational linguistics. As such, we argue that language models present a theoretically (and practically) sound approach that is our current best bet for computers to achieve language understanding. This understanding must however be understood as a computational means to an end.
|
|
