Challenges and opportunities of multimodal data in human learning: The computer science students' perspective

Multimodal data have the potential to explore emerging learning practices that extend human cognitive capacities. A critical issue stretching in many multimodal learning analytics (MLA) systems and studies is the current focus aimed at supporting researchers to model learner behaviours, rather than directly supporting learners. Moreover, many MLA systems are designed and deployed without learners' involvement. We argue that in order to create MLA interfaces that directly support learning, we need to gain an expanded understanding of how multimodal data can support learners' authentic needs. We present a qualitative study in which 40 computer science students were tracked in an authentic learning activity using wearable and static sensors. Our findings outline learners' curated representations about multimodal data and the non-technical challenges in using these data in their learning practice. The paper discusses 10 dimensions that can serve as guidelines for researchers and designers to create effective and ethically aware student-facing MLA innovations.     

Supervised machine learning in multimodal learning analytics for estimating success in project‐based learning

Multimodal learning analytics provides researchers new tools and techniques to capture different types of data from complex learning activities in dynamic learning environments. This paper investigates the use of diverse sensors, including computer vision, user‐generated content, and data from the learning objects (physical computing components), to record high‐fidelity synchronised multimodal recordings of small groups of learners interacting. We processed and extracted different aspects of the students' interactions to answer the following question: Which features of student group work are good predictors of team success in open‐ended tasks with physical computing? To answer this question, we have explored different supervised machine learning approaches (traditional and deep learning techniques) to analyse the data coming from multiple sources. The results illustrate that state‐of‐the‐art computational techniques can be used to generate insights into the "black box" of learning in students' project‐based activities. The features identified from the analysis show that distance between learners' hands and faces is a strong predictor of students' artefact quality, which can indicate the value of student collaboration. Our research shows that new and promising approaches such as neural networks, and more traditional regression approaches can both be used to classify multimodal learning analytics data, and both have advantages and disadvantages depending on the research questions and contexts being investigated. The work presented here is a significant contribution towards developing techniques to automatically identify the key aspects of students success in project‐based learning environments, and to ultimately help teachers provide appropriate and timely support to students in these fundamental aspects.     

Label distribution for multimodal machine learning

Multimodal machine learning(MML)aims to understand the world from multiple related modalities.It has attracted much attention as multimodal data has become increasingly available in real-world application.It is shown that MML can perform better than single-modal machine learning,since multi-modalities containing more information which could complement each other.However,it is a key challenge to fuse the multi-modalities in MML.Different from previous work,we further consider the side-information,which reflects the situation and influences the fusion of multi-modalities.We recover multimodal label distribution(MLD)by leveraging the side-information,representing the degree to which each modality contributes to describing the instance.Accordingly,a novel framework named multimodal label distribution learning(MLDL)is proposed to recover the MLD,and fuse the multimodalities with its guidance to learn an in-depth understanding of the jointly feature representation.Moreover,two versions of MLDL are proposed to deal with the sequential data.Experiments on multimodal sentiment analysis and disease prediction show that the proposed approaches perform favorably against state-of-the-art methods.     

Role of personality in computer based learning

With the rapid growth of technology enhanced learning, new mediums for learning have emerged. One of these mediums is computer based learning where the main concern is how to design a computer based learning system which takes into consideration the learners' differences. Personality is considered as one of the most critical sources of individual differences. This study investigates how personality differences within learners can affect computer based learning, through a comprehensive review of the literature. The highlighted results from the obtained nineteen studies are: (a) the most referred to personality model in computer based learning is MBTI; (b) personality traits affect how learners prefer learning content and learning approach like collecting information, communicating with instructor and peer, study behavior, acting and performing; (c) a new model of personality variables should be considered in computer based learning by taking all interested researchers and practitioners into accounts; and (d) the traditional questionnaire approach which is still the pre-dominant method to identify the learner's personality; and this needs to be changed with new potential of big data and learning analytics. Furthermore, this study presents a new implicit approach using learning analytics instead of questionnaire-based approach to identify the learner's personality.     

数据受限条件下的多模态处理技术综述

随着多媒体技术的发展,可获取的媒体数据在种类和量级上大幅提升。受人类感知方式的启发,多种媒体数据互相融合处理,促进了人工智能在计算机视觉领域的研究发展,在遥感图像解译、生物医学和深度估计等方面有广泛的应用。尽管多模态数据在描述事物特征时具有明显优势,但仍面临着较大的挑战。1）受到不同成像设备和传感器的限制,难以收集到大规模、高质量的多模态数据集;2）多模态数据需要匹配成对用于研究,任一模态的缺失都会造成可用数据的减少;3）图像、视频数据在处理和标注上需要耗费较多的时间和人力成本,这些问题使得目前本领域的技术尚待攻关。本文立足于数据受限条件下的多模态学习方法,根据样本数量、标注信息和样本质量等不同的维度,将计算机视觉领域中的多模态数据受限方法分为小样本学习、缺乏强监督标注信息、主动学习、数据去噪和数据增强5个方向,详细阐述了各类方法的样本特点和模型方法的最新进展。并介绍了数据受限前提下的多模态学习方法使用的数据集及其应用方向（包括人体姿态估计、行人重识别等）,对比分析了现有算法的优缺点以及未来的发展方向,对该领域的发展具有积极的意义。     

基于多模态多标记迁移学习的早期阿尔茨海默病诊断

针对当前基于机器学习的早期阿尔茨海默病（AD）诊断中训练样本不足的问题,提出一种基于多模态特征数据的多标记迁移学习方法,并将其应用于早期阿尔茨海默病诊断。所提方法框架主要包括两大模块：多标记迁移学习特征选择模块和多模态多标记分类回归学习器模块。首先,通过稀疏多标记学习模型对分类和回归学习任务进行有效结合;然后,将该模型扩展到来自多个学习领域的训练集,从而构建出多标记迁移学习特征选择模型;接下来,针对异质特征空间的多模态特征数据,采用多核学习技术来组合多模态特征核矩阵;最后,为了构建能同时用于分类与回归的学习模型,提出多标记分类回归学习器,从而构建出多模态多标记分类回归学习器。在国际老年痴呆症数据库（ADNI）进行实验,分类轻度认知功能障碍（MCI）最高平均精度为79.1%,预测神经心理学量表测试评分值最大平均相关系数为0.727。实验结果表明,所提多模态多标记迁移学习方法可以有效利用相关学习领域训练数据,从而提高早期老年痴呆症诊断性能。     

视觉语言多模态预训练综述

在多模态机器学习领域,为特定任务而制作的人工标注数据昂贵,且不同任务难以进行迁移,从而需要大量重新训练,导致训练多个任务时效率低下、资源浪费。预训练模型通过以自监督为代表的方式进行大规模数据训练,对数据集中不同模态的信息进行提取和融合,以学习其中蕴涵的通用知识表征,从而服务于广泛的相关下游视觉语言多模态任务,这一方法逐渐成为人工智能各领域的主流方法。依靠互联网所获取的大规模图文对与视频数据,以及以自监督学习为代表的预训练方法的进步,视觉语言多模态预训练模型在很大程度上打破了不同视觉语言任务之间的壁垒,提升了多个任务训练的效率并促进了具体任务的性能表现。本文总结视觉语言多模态预训练领域的进展,首先对常见的预训练数据集和预训练方法进行汇总,然后对目前最新方法以及经典方法进行系统概述,按输入来源分为图像—文本预训练模型和视频—文本多模态模型两大类,阐述了各方法之间的共性和差异,并将各模型在具体下游任务上的实验情况进行汇总。最后,总结了视觉语言预训练面临的挑战和未来发展趋势。     

Multimodal Co-learning: Challenges,applications with datasets,recent advances and future directions

Multimodal deep learning systems that employ multiple modalities like text, image, audio, video, etc., are showing better performance than individual modalities (i.e., unimodal) systems. Multimodal machine learning involves multiple aspects: representation, translation, alignment, fusion, and co-learning. In the current state of multimodal machine learning, the assumptions are that all modalities are present, aligned, and noiseless during training and testing time. However, in real-world tasks, typically, it is observed that one or more modalities are missing, noisy, lacking annotated data, have unreliable labels, and are scarce in training or testing, and or both. This challenge is addressed by a learning paradigm called multimodal co-learning. The modeling of a (resource-poor) modality is aided by exploiting knowledge from another (resource-rich) modality using the transfer of knowledge between modalities, including their representations and predictive models.Co-learning being an emerging area, there are no dedicated reviews explicitly focusing on all challenges addressed by co-learning. To that end, in this work, we provide a comprehensive survey on the emerging area of multimodal co-learning that has not been explored in its entirety yet. We review implementations that overcome one or more co-learning challenges without explicitly considering them as co-learning challenges. We present the comprehensive taxonomy of multimodal co-learning based on the challenges addressed by co-learning and associated implementations. The various techniques, including the latest ones, are reviewed along with some applications and datasets. Additionally, we review techniques that appear to be similar to multimodal co-learning and are being used primarily in unimodal or multi-view learning. The distinction between them is documented. Our final goal is to discuss challenges and perspectives and the important ideas and directions for future work that we hope will benefit for the entire research community focusing on this exciting domain.     

Advanced data science toolkit for non-data scientists – A user guide

Emerging modern data analytics attracts much attention in materials research and shows great potential for enabling data-driven design. Data populated from the high-throughput CALPHAD approach enables researchers to better understand underlying mechanisms and to facilitate novel hypotheses generation, but the increasing volume of data makes the analysis extremely challenging. Herein, we introduce an easy-to-use, versatile, and open-source data analytics frontend, ASCENDS (Advanced data SCiENce toolkit for Non-Data Scientists), designed with the intent of accelerating data-driven materials research and development. The toolkit is also of value beyond materials science as it can analyze the correlation between input features and target values, train machine learning models, and make predictions from the trained surrogate models of any scientific dataset. Various algorithms implemented in ASCENDS allow users performing quantified correlation analyses and supervised machine learning to explore any datasets of interest without extensive computing and data science background. The detailed usage of ASCENDS is introduced with an example of experimental high-temperature alloy data.     

基于多任务学习的时序多模态情感分析模型

针对时序多模态情感分析中存在的单模态特征表示和跨模态特征融合问题,结合多头注意力机制,提出一种基于多任务学习的情感分析模型。首先,使用卷积神经网络（CNN）、双向门控循环神经网络（BiGRU）和多头自注意力（MHSA）实现了对时序单模态的特征表示;然后,利用多头注意力实现跨模态的双向信息融合;最后,基于多任务学习思想,添加额外的情感极性分类和情感强度回归任务作为辅助,从而提升情感评分回归主任务的综合性能。实验结果表明,相较于多模态分解模型,所提模型的二分类准确度指标在CMU-MOSEI和CMU-MOSI多模态数据集上分别提高了7.8个百分点和3.1个百分点。该模型适用于多模态场景下的情感分析问题,能够为商品推荐、股市预测、舆情监控等应用提供决策支持。     

Harnessing Artificial Intelligence to Deliver Real-Time Intelligence and Business Process Improvements

As demand for data scientists in audit/Governance, risk management and compliance (GRC), and industry in general, outpaces supply, data science in a box—packaged analytics powered by artificial intelligence (AI) and guided machine learning—can bridge the gap to bring analytics to every major enterprise. Packaged analytics harness the power of AI and machine learning technologies to help operations, finance executives, and GRC professionals do their jobs better; optimize business processes; and deliver actionable insights for better decision making. This article will explore real-world case studies of how companies have used packaged analytics to achieve process improvements, better oversight over financial spend, and significant return on investment. It is a guide to internal auditors and their GRC counterparts on what is available and suggests they can partner or use the products independently and significantly contribute to their companies.     

支持深度学习的视觉数据库管理系统研究进展

计算机视觉因其强大的学习能力,在各种真实场景中得到了广泛应用.随着数据库的发展,利用数据库中成熟的数据管理技术来处理视觉分析应用,已成为一种日益增长的研究趋势.图像、视频和文本等多模态数据的相互融合处理,也促进了视觉分析应用的多样性和准确性.近年来,因深度学习的兴起,支持深度学习的视觉分析应用开始受到广泛关注.然而,传统的数据库管理技术在深度学习场景下面临着复杂视觉分析语义难以表达、应用执行效率低等问题.因此,支持深度学习的视觉数据库管理系统得到了广泛关注.综述了目前视觉数据库管理系统的研究进展:首先,总结了视觉数据库管理系统在不同层面上面临的挑战,包括编程接口、查询优化、执行调度和数据存储;其次,分别探讨了上述4个层面上的相关技术;最后,对视觉数据库管理系统未来的研究方向进行了展望.     

Context counts: How learners' contexts influence learning in a MOOC

Massive Open Online Courses (MOOCs) require individual learners to self-regulate their own learning, determining when, how and with what content and activities they engage. However, MOOCs attract a diverse range of learners, from a variety of learning and professional contexts. This study examines how a learner's current role and context influences their ability to self-regulate their learning in a MOOC: Introduction to Data Science offered by Coursera. The study compared the self-reported self-regulated learning behaviour between learners from different contexts and with different roles. Significant differences were identified between learners who were working as data professionals or studying towards a higher education degree and other learners in the MOOC. The study provides an insight into how an individual's context and role may impact their learning behaviour in MOOCs.     

Enhancing multimodal learning through personalized gesture recognition

Gestural recognition systems are important tools for leveraging movement‐based interactions in multimodal learning environments but personalizing these interactions has proven difficult. We offer an adaptable model that uses multimodal analytics, enabling students to define their physical interactions with computer‐assisted learning environments. We argue that these interactions are foundational to developing stronger connections between students' physical actions and digital representations within a multimodal space. Our model uses real time learning analytics for gesture recognition, training a hierarchical hidden‐Markov model with a “one‐shot” construct, learning from user‐defined gestures, and accessing 3 different modes of data: skeleton positions, kinematics features, and internal model parameters. Through an empirical comparison with a “pretrained” model, we show that our model can achieve a higher recognition accuracy in repeatability and recall tasks. This suggests that our approach is a promising way to create productive experiences with gesture‐based educational simulations, promoting personalized interfaces, and analytics of multimodal learning scenarios.     

Bridging systems theory and data science: A unifying review of dynamic latent variable analytics and process monitoring

This paper is concerned with data science and analytics as applied to data from dynamic systems for the purpose of monitoring, prediction, and inference. Collinearity is inevitable in industrial operation data. Therefore, we focus on latent variable methods that achieve dimension reduction and collinearity removal. We present a new dimension reduction expression of state space framework to unify dynamic latent variable analytics for process data, dynamic factor models for econometrics, subspace identification of multivariate dynamic systems, and machine learning algorithms for dynamic feature analysis. We unify or differentiate them in terms of model structure, objectives with constraints, and parsimony of parameterization. The Kalman filter theory in the latent space is used to give a system theory foundation to some empirical treatments in data analytics. We provide a unifying review of the connections among the dynamic latent variable methods, dynamic factor models, subspace identification methods, dynamic feature extractions, and their uses for prediction and process monitoring. Both unsupervised dynamic latent variable analytics and the supervised counterparts are reviewed. Illustrative examples are presented to show the similarities and differences among the analytics in extracting features for prediction and monitoring.     

复杂网络的双曲空间表征学习方法

复杂网络在现实场景中无处不在，高效的复杂网络分析技术具有广泛的应用价值，比如社区检测、链路预测等.然而直接对大规模的复杂网络邻接矩阵进行分析需要较高的时间、空间复杂度，网络表征学习是一种解决此问题的有效方法.该类方法将高维稀疏的网络信息转化为低维稠密的实值向量，可以作为机器学习算法的输入，便于后续应用的高效计算.传统的网络表征学习方法将实体对象嵌入到低维欧氏向量空间中，但复杂网络是一类具有近似树状层次结构、幂率度分布、强聚类特性的网络，该结构更适合用具有负曲率的双曲空间来描述.本文将针对复杂网络的双曲空间表征学习方法进行系统性的介绍和总结.     

Micro-persistence and difficulty in a game-based learning environment for computational thinking acquisition

Persistence has been identified as a crucial quality of learning. However, it is hard to attain in online game-based environments as the drive to progress in the game may influence the ability to achieve the learning goals. This study aimed to examine the associations between micro-persistence, that is, the tendency to complete an individual task successfully, and task difficulty while acquiring computational thinking (CT). We further explored whether contextual or personal attributes better explain micro-persistence. We analysed data of 111 school students who used the CodeMonkey platform. We took a learning analytics approach for analysing the platform's log files. We found that micro-persistence is associated with task difficulty and that students who demonstrated an aptitude to learn new material are motivated to achieve the best solution. We also found that contextual variables better-explained micro-persistence than personal attributes. Encouraging micro-persistence can improve CT acquisition and the learning processes involved.     

The State‐of‐the‐Art in Predictive Visual Analytics

Predictive analytics embraces an extensive range of techniques including statistical modeling, machine learning, and data mining and is applied in business intelligence, public health, disaster management and response, and many other fields. To date, visualization has been broadly used to support tasks in the predictive analytics pipeline. Primary uses have been in data cleaning, exploratory analysis, and diagnostics. For example, scatterplots and bar charts are used to illustrate class distributions and responses. More recently, extensive visual analytics systems for feature selection, incremental learning, and various prediction tasks have been proposed to support the growing use of complex models, agent‐specific optimization, and comprehensive model comparison and result exploration. Such work is being driven by advances in interactive machine learning and the desire of end‐users to understand and engage with the modeling process. In this state‐of‐the‐art report, we catalogue recent advances in the visualization community for supporting predictive analytics. First, we define the scope of predictive analytics discussed in this article and describe how visual analytics can support predictive analytics tasks in a predictive visual analytics (PVA) pipeline. We then survey the literature and categorize the research with respect to the proposed PVA pipeline. Systems and techniques are evaluated in terms of their supported interactions, and interactions specific to predictive analytics are discussed. We end this report with a discussion of challenges and opportunities for future research in predictive visual analytics.     

VA + Embeddings STAR: A State-of-the-Art Report on the Use of Embeddings in Visual Analytics

Over the past years, an increasing number of publications in information visualization, especially within the field of visual analytics, have mentioned the term “embedding” when describing the computational approach. Within this context, embeddings are usually (relatively) low-dimensional, distributed representations of various data types (such as texts or graphs), and since they have proven to be extremely useful for a variety of data analysis tasks across various disciplines and fields, they have become widely used. Existing visualization approaches aim to either support exploration and interpretation of the embedding space through visual representation and interaction, or aim to use embeddings as part of the computational pipeline for addressing downstream analytical tasks. To the best of our knowledge, this is the first survey that takes a detailed look at embedding methods through the lens of visual analytics, and the purpose of our survey article is to provide a systematic overview of the state of the art within the emerging field of embedding visualization. We design a categorization scheme for our approach, analyze the current research frontier based on peer-reviewed publications, and discuss existing trends, challenges, and potential research directions for using embeddings in the context of visual analytics. Furthermore, we provide an interactive survey browser for the collected and categorized survey data, which currently includes 122 entries that appeared between 2007 and 2023.     

Teacher regulation of cognitive activities during student collaboration: Effects of learning analytics

By collaboratively solving a task, students are challenged to share ideas, express their thoughts, and engage in discussion. Collaborating groups of students may encounter problems concerning cognitive activities (such as a misunderstanding of the task material). If these problems are not addressed and resolved in time, the collaborative process is hindered. The teacher plays an important role in monitoring and solving the occurrence of problems. To provide adaptive support, teachers continuously have to be aware of students' activities in order to identify relevant events, including those that require intervention. Because the amount of available information is high, teachers may be supported by learning analytics. The present experimental study (n = 40) explored the effect of two learning analytics tools (the Concept Trail and Progress Statistics) that give information about students' cognitive activities. The results showed that when teachers had access to learning analytics, they were not better at detecting problematic groups, but they did offer more support in general, and more specifically targeted groups that experienced problems. This could indicate that learning analytics increase teachers' confidence to act, which in turn means students could benefit more from the teacher's presence.