Knowledge interdependence with the partner, accuracy of mutual knowledge model and computer-supported collaborative learning

The present study is part of a project aiming at empirically investigating the process of modeling the partner’s knowledge (Mutual Knowledge Modeling or MKM) in Computer-Supported Collaborative Learning (CSCL) settings. In this study, a macro-collaborative script was used to produce knowledge interdependence (KI) among colearners by providing them with different but complementary information. Prior to collaboration, two students read the same text in the “Same Information” (SI) condition while each of them read one of two complementary texts in the “Complementary Information” (CI) condition. After the collaboration phase, a knowledge modeling questionnaire asked participants to estimate both their own — and their partner’s outcome knowledge thanks to Likert-type scales. The relation between the accuracy with which co-learners assess their partner’s knowledge and learning has been examined. In addition, we investigated the KI effect on (a) learning performance and (b) the MKM accuracy. Finally, we wondered to what extent the MKM accuracy could mediate the KI effect on learning. Results showed no difference in learning performance between participants who worked on same information and participants who worked on complementary information. We also found that participants were more accurate at assessing their partner’s knowledge in the SI condition than in the CI condition. The discussion focuses on methodological limitations and provides new directions for investigating the KI effect on MKM accuracy.

Mapping biological ideas: Concept maps as knowledge integration tools for evolution education

Beat Adrian Schwendimann

Many students leave school with a fragmented understanding of biology that does not allow them to connect their ideas to their everyday lives (Wandersee, 1989; Mintzes, Wandersee, & Novak, 1998; Mintzes, Wandersee, & Novak, 2000a). Understanding evolution ideas is seen as central to building an integrated knowledge of biology (Blackwell, Powell, & Dukes, 2003; Thagard & Findlay, 2010). However, the theory of evolution has been found difficult to understand as it incorporates a wide range of ideas from different areas (Bahar et al., 1999; Tsui & Treagust, 2003) and multiple interacting levels (Wilensky & Resnick, 1999; Duncan & Reiser, 2007; Hmelo-Silver et al., 2007). Research suggests that learners can hold a rich repertoire of co-existing alternative ideas of evolution (for example, Bishop & Anderson, 1990; Demastes, Good, & Peebles, 1996; Evans, 2008), especially of human evolution (for example, Nelson, 1986; Sinatra et al., 2003; Poling & Evans, 2004). Evolution ideas are difficult to understand because they often contradict existing alternative ideas (Mayr, 1982; Wolpert, 1994; Evans, 2008). Research suggests that understanding human evolution is a key to evolution education (for example, Blackwell et al., 2003; Besterman & Baggott la Velle, 2007). This dissertation research investigates how different concept mapping forms embedded in a collaborative technology-enhanced learning environment can support students’ integration of evolution ideas using case studies of human evolution. Knowledge Integration (KI) (Linn et al., 2000; Linn et al., 2004) is used as the operational framework to explore concept maps as knowledge integration tools to elicit, add, critically distinguish, group, connect, and sort out alternative evolution ideas. Concept maps are a form of node-link diagram for organizing and representing connections between ideas as a semantic network (Novak & Gowin, 1984). This dissertation research describes the iterative development of a novel biology-specific form of concept map, called Knowledge Integration Map (KIM), which aims to help learners connect ideas across levels (for example, genotype and phenotype levels) towards an integrated understanding of evolution. Using a design-based research approach (Brown, 1992; Cobb et al., 2003), three iterative studies were implemented in ethnically and economically diverse public high schools classrooms using the web-based inquiry science environment (WISE) (Linn et al., 2003; Linn et al., 2004). Study 1 investigates concept maps as generative assessment tools. Study 1A compares the concept map generation and critique process of biology novices and experts. Findings suggest that concept maps are sensitive to different levels of knowledge integration but require scaffolding and revision. Study 1B investigates the implementation of concept maps as summative assessment tools in a WISE evolution module. Results indicate that concept maps can reveal connections between students’ alternative ideas of evolution. Study 2 introduces KIMs as embedded collaborative learning tools. After generating KIMs, student dyads revise KIMs through two different critique activities (comparison against an expert or peer generated KIM). Findings indicate that different critique activities can promote the use of different criteria for critique. Results suggest that the combination of generating and critiquing KIMs can support integrating evolution ideas but can be time-consuming. As time in biology classrooms is limited, study 3 distinguishes the learning effects from either generating or critiquing KIMs as more time efficient embedded learning tools. Findings suggest that critiquing KIMs can be more time efficient than generating KIMs. Using KIMs that include common alternative ideas for critique activities can create genuine opportunities for students to critically reflect on new and existing ideas. Critiquing KIMs can encourage knowledge integration by fostering self-monitoring of students’ learning progress, identifying knowledge gaps, and distinguishing alternative evolution ideas. This dissertation research demonstrates that science instruction of complex topics, such as human evolution, can succeed through a combination of scaffolded inquiry activities using dynamic visualizations, explanation activities, and collaborative KIM activities. This research contributes to educational research and practice by describing ways to make KIMs effective and time efficient learning tools for evolution education. Supporting students’ building of a more coherent understanding of core ideas of biology can foster their life-long interest and learning of science.

University of California, Berkeley2011

Prior knowledge in Kernel methods

Alexei Pozdnoukhov

Machine Learning is a modern and actively developing field of computer science, devoted to extracting and estimating dependencies from empirical data. It combines such fields as statistics, optimization theory and artificial intelligence. In practical tasks, the general aim of Machine Learning is to construct algorithms able to generalize and predict in previously unseen situations based on some set of examples. Given some finite information, Machine Learning provides ways to exract knowledge, describe, explain and predict from data. Kernel Methods are one of the most successful branches of Machine Learning. They allow applying linear algorithms with well-founded properties such as generalization ability, to non-linear real-life problems. Support Vector Machine is a well-known example of a kernel method, which has found a wide range of applications in data analysis nowadays. In many practical applications, some additional prior knowledge is often available. This can be the knowledge about the data domain, invariant transformations, inner geometrical structures in data, some properties of the underlying process, etc. If used smartly, this information can provide significant improvement to any data processing algorithm. Thus, it is important to develop methods for incorporating prior knowledge into data-dependent models. The main objective of this thesis is to investigate approaches towards learning with kernel methods using prior knowledge. Invariant learning with kernel methods is considered in more details. In the first part of the thesis, kernels are developed which incorporate prior knowledge on invariant transformations. They apply when the desired transformation produce an object around every example, assuming that all points in the given object share the same class. Different types of objects, including hard geometrical objects and distributions are considered. These kernels were then applied for images classification with Support Vector Machines. Next, algorithms which specifically include prior knowledge are considered. An algorithm which linearly classifies distributions by their domain was developed. It is constructed such that it allows to apply kernels to solve non-linear tasks. Thus, it combines the discriminative power of support vector machines and the well-developed framework of generative models. It can be applied to a number of real-life tasks which include data represented as distributions. In the last part of the thesis, the use of unlabelled data as a source of prior knowledge is considered. The technique of modelling the unlabelled data with a graph is taken as a baseline from semi-supervised manifold learning. For classification problems, we use this apporach for building graph models of invariant manifolds. For regression problems, we use unlabelled data to take into account the inner geometry of the input space. To conclude, in this thesis we developed a number of approaches for incorporating some prior knowledge into kernel methods. We proposed invariant kernels for existing algorithms, developed new algorithms and adapted a technique taken from semi-supervised learning for invariant learning. In all these cases, links with related state-of-the-art approaches were investigated. Several illustrative experiments were carried out on real data on optical character recognition, face image classification, brain-computer interfaces, and a number of benchmark and synthetic datasets.

EPFL2006

Many Are The Ways to Learn: Identifying multi-modal behavioral profiles of collaborative learning in constructivist activities

Barbara Bruno, Pierre Dillenbourg, Aditi Kothiyal, Jauwairia Nasir

Understanding how learners engage with learning technologies, and its relation with their learning, is crucial to the design of effective learning interventions. Assessing the learners’ state however, is non-trivial. Research suggests that performance is not always a good indicator of learning, especially with open-ended constructivist activities. In this paper, we describe a combined multi-modal learning analytics and interaction analysis method which uses video, audio and log data to identify multi-modal collaborative learning behavioral profiles of 32 dyads as they work on an open-ended task around interactive tabletops with a robot mediator. These profiles, that we name Expressive Explorers, Calm Tinkerers, and Silent Wanderers, confirm previous findings that in a collaborative setting, the amount of speech interaction and the overlap of speech between a pair of learners are highly discriminating behaviors between learning and non-learning pairs, signifying that overlapping speech while turn-taking can indicate engagement that is conducive to learning. However, additionally considering learner affect and actions during the task helps us identify that there exist multiple behavioural profiles exhibited even among those who learn. Specifically, we discover that those who learn vary in their behaviors along the two dimensions of problem solving strategy (actions) and emotional expressivity (affect), suggesting that there is a relation between problem solving strategy and emotional behaviour; one strategy leads to more frustration compared to another. These findings have implications for the design of real-time learning interventions that support productive collaborative learning in open-ended tasks.