Discussion Mining: Annotation-Based Knowledge Discovery from Real World Activities

Proceedings of the 10th International Conference on Computer Supported Education

2018

Self Cite

Heart rate (HR) variability (HRV) has recently seen a surge in interest regarding the evaluation of cognitive performance as it always be used to measure the autonomic nervous system function. In this study, we argue that a presenters' HR data can be used to effectively evaluate their cognitive performance, specifically presenters' performance of discussion which consists of several Q&A segments (question and answer pairs) compared with using traditional natural language processing (NLP) such as semantic analysis. To confirm this, we used a non-invasive device, i.e., Apple Watch, to collect real-time updated HR data of presenters during discussions in our lab-seminar environment, their HR data were analyzed based on Q&A segments, and three machine-learning models were generated for evaluation: logistic regression, support vector machine, and random forest. We also discuss the meaningful HR and HRV features (metrics). Comparative experiments were conducted involving semantic data of Q&A statements alone and a combination of HR and semantic data. The HR data of presenters resulted in effective evaluation of discussion performance compared with using only semantic data. The combination of these two types of data could improve the discussion performance evaluation ability to some extent.

Section: Discussion-mining Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Evaluation of Presenters’ Discussion Performance based on Their Heart Rate

Peng

Proceedings of the 10th International Conference on Computer Supported Education

2018

Self Cite

“…This previously developed system Nagao et al (2005), shown in Figure 5, generates structured minutes for meetings semi-automatically and links them with audiovisual data. This system summarizes discussions using a personal device, which captures information, called the discussion commander.…”

Section: Discussion Mining Systemmentioning

confidence: 99%

Tools and evaluation methods for discussion and presentation skills training

Tehrani

Fajardo

2015

Smart Learn. Environ.

Self Cite

Our university is currently developing an advanced physical-digital learning environment that can train students to enhance their discussion and presentation skills. The environment guarantees an efficient discussion among users with state-of-the-art technologies such as touch panel discussion tables, digital posters, and an interactive wall-sized whiteboard. It includes a data mining system that efficiently records, summarizes, and annotates discussions held inside our facility. We also developed a digital poster authoring tool, a novel tool for creating interactive digital posters displayed using our digital poster presentation system. Evaluation results show the efficiency of using our facilities: the data mining system and the digital poster authoring tool. In addition, our physical-digital learning environment will be further enhanced with a vision system that will detect interactions with the digital poster presentation system and the different discussion tools enabling a more automated skill evaluation and discussion mining.

“…Our laboratory has been developing and operating a system to record seminar content [11]. Generally, proceedings of a seminar consist of an abstract and hand-outs, but seminar content can also include a summarized transcript, audio or video recordings of the seminar, or the slides used in the presentation.…”

Section: Research Activitymentioning

confidence: 99%

Task Execution Support in Research Activity using RAC System

Ohira

Morita

Annals of Computer Science and Information Systems

2017

Self Cite

Abstract-Research activities carried out daily in research laboratories, include conducting investigations, giving seminars on progress, performing experiments, analyzing results, and writing papers, but all of these research activities involve steady, methodical work that does not produce immediate, visible results. For this reason, a mechanism to maintain motivation when research is not going well or to help students get on track with research when they have just been assigned to a laboratory could be useful. Students that have just begun their research may not yet understand how to proceed. We previously developed a research activity concierge (RAC) system, which is a platform to encompass general research activities, and applied gamification to this system to keep user motivation high. However, even with the RAC, non-research-savvy students have difficulty handling challenges and executing tasks. In this research, we focused on discussions in seminars and introduced a mechanism to support task execution in students' research activities by implementing automatic extraction of task statements into the RAC.