Developing a Framework for Integrating Prior Problem Solving and Knowledge Sharing Histories of a Group to Predict Future Group Performance

Stevens, Ron; Soller, Amy; Giordani, Alessandra; Gerosa, Luca; Cooper, Melanie M.; Cox, Charles T.

doi:10.1109/colcom.2005.1651209

Cited by 8 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, they are two different application stages. The first stage mainly concentrates on preliminary knowledge discovery with qualitative problem cognition [3][5] [7] [8]. The second stage mainly focuses on verifying the problem specification derived from the first stage, through concrete parameter computing activities [6] [9][10] [11].…”

Section: Introductionmentioning

confidence: 99%

A Novel Knowledge Modeling Framework POTMe and Its Application for Col-laborative Problem Solving

Jiang¹

2016

Proceedings of the 2015 4th National Conference on Electrical, Electronics and Computer Engineering

View full text Add to dashboard Cite

Abstract. Collaborative efforts are inevitably demanded when solving a complex problem, which is often plagued with incomplete, ill-structured, and poor quality information. Therefore, a global knowledge modeling framework is required for cross-domain knowledge coordination. However, current knowledge modeling techniques pay little attention to temporal knowledge that is indispensable for navigating cross-domain collaborative task executions and their collaboration. In view of this challenge, a novel knowledge modeling framework, named POTMe, is investigated in this paper. This knowledge modeling framework provides a structured application context by articulating knowledge dependencies and temporal dependencies among problemsolving activities. The main contribution of this paper is twofold. First, this novel knowledge modeling framework provides a structured problem solving context. It enhances the consistency of global knowledge coordination among collaborative problem-solving activities. Second, temporal knowledge modeling is incorporated into this knowledge modeling framework. It is reified by a temporal reasoning rule, and aims at evaluating cross-domain task collaboration in an incorporated executive environment. [3] believed that a human-engineered activity could be characterized by three traditional engineering activities, i.e., 1) stakeholders define their needs and requirements, 2) engineers design the product based on stakeholders' definitions, and 3) producers build the product based on engineers' designs. These activities are often accompanied by cross-domain knowledge sharing and collaboration. The first and second activities could be characterized by product conceiving behaviors. The third activity could be featured by product producing behavior based on the product blueprint. IntroductionIn collaborative problem solving, qualitative problem-defining process equal to a group of product conceiving behaviors, while quantitative parameter computing and verifying process could be treated as a group of product producing behaviors. Generally, they are two different application stages. The first stage mainly concentrates on preliminary knowledge discovery with qualitative problem cognition . In practice, a complex problem and its collaboration solving are often initiated by incomplete, ill structured and poor quality information. It is always a challenging endeavor

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Knowledge Modeling Framework POTMe and Its Application for Col-laborative Problem Solving

Jiang¹

2016

Proceedings of the 2015 4th National Conference on Electrical, Electronics and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…This performance can be understood in very different ways such as the number of errors made by students in exams, final grades, students' marks in a subject, and so forth. Examples of approaches to predict students' marks -which is the purpose of this paper-includes neural networks [8], [9], Bayesian networks [10], [11], rule-based techniques [12], [13], linear regression [14], and so forth. For the purpose of this paper, the main drawback of these approaches it that they do not focus on predicting the fulfillment of the educational objectives of a course, as they assume that each educational objective is related to an only learning activity, and vice versa.…”

Section: Introductionmentioning

confidence: 99%

Learning analytics for the prediction of the educational objectives achievement

Fernández-Delgado

Mucientes

Vázquez-Barreiros

et al. 2014

2014 IEEE Frontiers in Education Conference (FIE) Proceedings

View full text Add to dashboard Cite

Prediction of students' performance is one of the most explored issues in educational data mining. To predict if students will achieve the outcomes of the subject based on the previous results enables teachers to adapt the learning design of the subject to the teaching-learning process. However, this adaptation is even more relevant if we could predict the fulfillment of the educational objectives of a subject, since teachers should focus the adaptation on the learning resources and activities related to those educational objectives. In this paper, we present an experiment where a support vector machine is applied as a classifier that predicts if the different educational objectives of a subject are achieved or not. The inputs of the problem are the marks obtained by the students in the questionnaires related to the learning activities that students must undertake during the course. The results are very good, since the classifiers predict the achievement of the educational objectives with precision over 80%.

show abstract

“…The work from Stevens et al . () differs from the ones presented earlier by focusing on modelling team effectiveness and estimating the team problem‐solving ability of chemistry students. The authors developed a synchronous and symmetrical collaborative extension to the online IMMEX problem‐solving environment, simulating a face‐to‐face collaboration episode that recorded input actions while students solved a series of problem simulations.…”

Section: Introductionmentioning

confidence: 99%

Predicting teamwork results from social network analysis

Crespo

Antunes

2013

Expert Systems

View full text Add to dashboard Cite

Modelling students' behaviours has reached a status that can only be overcome by improving the ability of predicting the results on teamwork. Indeed, teamwork is an important piece on the learning process, but understanding their mechanisms and predicting the results achieved is far from being solved by traditional classifiers. In this paper, we address the problem of predicting teamwork results, and propose a recommender system that suggests new teams, in the context of a given curricular unit. Any student, who is looking for a team, may use the system; in particular, he may ask for the best team to join, either considering all available colleagues or just the set of his previous teammates. Our system makes use of social network analysis and classification methods as the algorithmic core of the decision-making process. System evaluation is presented through a set of experimental results, which report the performance of social network analysis and classification algorithms over real datasets.

show abstract

Developing a Framework for Integrating Prior Problem Solving and Knowledge Sharing Histories of a Group to Predict Future Group Performance

Cited by 8 publications

References 19 publications

A Novel Knowledge Modeling Framework POTMe and Its Application for Col-laborative Problem Solving

A Novel Knowledge Modeling Framework POTMe and Its Application for Col-laborative Problem Solving

Learning analytics for the prediction of the educational objectives achievement

Predicting teamwork results from social network analysis

Contact Info

Product

Resources

About