The RAP system

Ochôa, Xavier; Domínguez, Federico; Guamán, Bruno; Maya, Ricardo; Falcones, Gabriel; Castells, Jaime

doi:10.1145/3170358.3170406

Cited by 59 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both Presentation Sensei (Kurihara, Goto, Ogata, Matsusaka, & Igarashi, 2007) and Cicero (Batrinca et al ., 2013; Wörtwein et al ., 2015) were only evaluated in this way. Newer systems, Gan, Wong, Mandal, Chandrasekhar, and Kankanhalli (2015), Autommaner (Tanveer, Zhao, Chen, Tiet, & Hoque, 2016) and RAP (Ochoa et al ., 2018), have their accuracy measured to establish if the automatically estimated values correlated with human annotations of the same features. All these evaluations have been laboratory‐based because the participants were not students or the setting was a non‐authentic learning activity.…”

Section: Previous Researchmentioning

confidence: 99%

“…An extended description of the system, technical details of its inner workings and an evaluation of the attitudes of students towards the system can be found in Ochoa et al . (2018).…”

Section: Description Of the Systemmentioning

confidence: 99%

“…While there are considerable examples of automated oral presentation feedback (Batrinca, Stratou, Shapiro, Morency, & Scherer, 2013; Damian et al ., 2015; Ochoa et al ., 2018; Schneider, Börner, van Rosmalen, & Specht, 2015; Trinh, Asadi, Edge, & Bickmore, 2017), there is no strong scientific evidence that they actually help with the development of oral presentation skills or if those skills developed with the system are transferred and evident in real‐world presentations (see next section for evidence). The main contribution of this work is to conduct the first large‐scale randomised controlled experiment in an authentic setting to test the effect that one of these systems, RAP (Ochoa et al ., 2018), has on the oral presentation performance of entry‐level higher education students.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Controlled evaluation of a multimodal system to improve oral presentation skills in a real learning setting

Ochôa¹,

Domínguez²

2020

Brit J Educational Tech

Self Cite

View full text Add to dashboard Cite

Developing oral presentation skills requires both practice and expert feedback. Several systems have been developed during the last 20 years to provide ample practice opportunities and automated feedback for novice presenters. However, a comprehensive literature review discovered that none of those systems have been adequately evaluated in real learning settings. This work is the first randomised controlled evaluation of the impact that one of these systems has in developing oral presentation skills during a real semester‐long learning activity with 180 students. The main findings are that (1) the development of different dimensions of the oral presentations are not affected equally by the automated feedback and (2) there is a small but statistically significant effect of the use of the tool when a subsequent presentation is evaluated by a human expert.

show abstract

Section: Previous Researchmentioning

confidence: 99%

“…An extended description of the system, technical details of its inner workings and an evaluation of the attitudes of students towards the system can be found in Ochoa et al . (2018).…”

Section: Description Of the Systemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Controlled evaluation of a multimodal system to improve oral presentation skills in a real learning setting

Ochôa¹,

Domínguez²

2020

Brit J Educational Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…As a consequence, students are often evaluated with respect to these presentations. One approach to oral presentation feedback is to use only low-cost sensors, to provide data from audio and video [10] or from audio and slides [35]. Kinect devices can also be used to collect data for presentation feedback.…”

Section: Related Workmentioning

confidence: 99%

“…Advanced sensors technologies allow for capturing biometric data with different modalities. This includes artifacts, such as gaze [9], postures [5,10], actions [11], facial expressions [12], speech [7,13], writing [14], and sketching [15]. These artifacts are examples of sources multimodal information that have been gradually incorporated into systems of learning.…”

Section: Introductionmentioning

confidence: 99%

Using Depth Cameras to Detect Patterns in Oral Presentations: A Case Study Comparing Two Generations of Computer Engineering Students

Roque

Cechinel

Weber

et al. 2019

Sensors

View full text Add to dashboard Cite

Speaking and presenting in public are critical skills for academic and professional development. These skills are demanded across society, and their development and evaluation are a challenge faced by higher education institutions. There are some challenges to evaluate objectively, as well as to generate valuable information to professors and appropriate feedback to students. In this paper, in order to understand and detect patterns in oral student presentations, we collected data from 222 Computer Engineering (CE) fresh students at three different times, over two different years (2017 and 2018). For each presentation, using a developed system and Microsoft Kinect, we have detected 12 features related to corporal postures and oral speaking. These features were used as input for the clustering and statistical analysis that allowed for identifying three different clusters in the presentations of both years, with stronger patterns in the presentations of the year 2017. A Wilcoxon rank-sum test allowed us to evaluate the evolution of the presentations attributes over each year and pointed out a convergence in terms of the reduction of the number of features statistically different between presentations given at the same course time. The results can further help to give students automatic feedback in terms of their postures and speech throughout the presentations and may serve as baseline information for future comparisons with presentations from students coming from different undergraduate courses.

show abstract