Dataset Information

Predicting Spatial Visualization Problems' Difficulty Level from Eye-Tracking Data.

ABSTRACT: The difficulty level of learning tasks is a concern that often needs to be considered in the teaching process. Teachers usually dynamically adjust the difficulty of exercises according to the prior knowledge and abilities of students to achieve better teaching results. In e-learning, because there is no teacher involvement, it often happens that the difficulty of the tasks is beyond the ability of the students. In attempts to solve this problem, several researchers investigated the problem-solving process by using eye-tracking data. However, although most e-learning exercises use the form of filling in blanks and choosing questions, in previous works, research focused on building cognitive models from eye-tracking data collected from flexible problem forms, which may lead to impractical results. In this paper, we build models to predict the difficulty level of spatial visualization problems from eye-tracking data collected from multiple-choice questions. We use eye-tracking and machine learning to investigate (1) the difference of eye movement among questions from different difficulty levels and (2) the possibility of predicting the difficulty level of problems from eye-tracking data. Our models resulted in an average accuracy of 87.60% on eye-tracking data of questions that the classifier has seen before and an average of 72.87% on questions that the classifier has not yet seen. The results confirmed that eye movement, especially fixation duration, contains essential information on the difficulty of the questions and it is sufficient to build machine-learning-based models to predict difficulty level.

SUBMITTER: Li X

PROVIDER: S-EPMC7180473 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Spatial Visualization Problems' Difficulty Level from Eye-Tracking Data.

Li Xiang X Younes Rabih R Bairaktarova Diana D Guo Qi Q

Sensors (Basel, Switzerland) 20200331 7

The difficulty level of learning tasks is a concern that often needs to be considered in the teaching process. Teachers usually dynamically adjust the difficulty of exercises according to the prior knowledge and abilities of students to achieve better teaching results. In e-learning, because there is no teacher involvement, it often happens that the difficulty of the tasks is beyond the ability of the students. In attempts to solve this problem, several researchers investigated the problem-solvi ...[more]

PMID: 32244360

Similar Datasets

Project description:To evaluate ease of use and usefulness for nurses of visualizations of infectious disease transmission in a hospital.An observational study was used to evaluate perceptions of several visualizations of data extracted from electronic health records designed using a participatory approach. Twelve nurses in the master's program in an urban research-intensive nursing school participated in May 2015.A convergent parallel mixed method was used to evaluate nurses' perceptions on ease of use and usefulness of five visualization conveying trends in hospital infection transmission applying think-aloud, interview, and eye-tracking techniques.Subjective data from the interview and think-aloud techniques indicated that participants preferred the traditional line graphs in simple data representation due to their familiarity, clarity, and easiness to read. An objective quantitative measure of eye movement analysis (444,421 gaze events) identified a high degree of participants' attention span in infographics in all three scenarios. All participants responded with the correct answer within 1 min in comprehensive tests.A user-centric approach was effective in developing and evaluating visualizations for hospital infection transmission. For the visualizations designed by the users, the participants were easily able to comprehend the infection visualizations on both line graphs and infographics for simple visualization. The findings from the objective comprehension test and eye movement and subjective attitudes support the feasibility of integrating user-centric visualization designs into electronic health records, which may inspire clinicians to be mindful of hospital infection transmission. Future studies are needed to investigate visualizations and motivation, and the effectiveness of visualization on infection rate.This study designed visualization images using clinical data from electronic health records applying a user-centric approach. The design insights can be applied for visualizing patient data in electronic health records.

Project description:BackgroundItem response theory (IRT; Lord & Novick, 1968) is a psychometric framework that can be used to model the likelihood that an individual will respond correctly to an item. Using archival data (Mirman et al., 2010), Fergadiotis, Kellough, and Hula (2015) estimated difficulty parameters for the Philadelphia Naming Test (PNT; Roach, Schwartz, Martin, Grewal, & Brecher, 1996) using the 1-parameter logistic IRT model. Although the use of IRT in test development is advantageous, its reliance on sample sizes exceeding 200 participants make it difficult to implement in aphasiology. Therefore, alternate means of estimating the item difficulty of confrontation naming test items warrant investigation. In a preliminary study aimed at automatic item calibration, Swiderski, Fergadiotis, and Hula (2016) regressed the difficulty parameters from the PNT on word length, age of acquisition (Kuperman et al., 2012), lexical frequency as quantified by the Log10CD index (Brysbaert & New, 2009), and naming latency (Székely et al., 2003). Although this model successfully explained a substantial proportion of variance in the PNT difficulty parameters, a substantial proportion (20%) of the response time data were missing. Further, only 39% of the picture stimuli from Székely and colleagues (2003) were identical to those on the PNT. Given that the IRT sample size requirements limit traditional calibration approaches in aphasiology and that the initial attempts in predicting IRT difficulty parameters in our pilot study were based on incomplete response time data this study has two specific aims.AimsTo estimate naming latencies for the 175 items on the PNT, and assess the utility of psycholinguistic variables and naming latencies for predicting item difficulty.Methods and proceduresUsing a speeded picture naming task we estimated mean naming latencies for the 175 items of the Philadelphia Naming test in 44 cognitively healthy adults. We then re-estimated the model reported by Swiderski et al (2016) with the new naming latency data.ResultsThe predictor variables described above accounted for a substantial proportion of the variance in the item difficulty parameters (Adj. R 2 = .692).ConclusionsIn this study we demonstrated that word length, age of acquisition, lexical frequency, and naming latency from neurotypical young adults usefully predict picture naming item difficulty in people with aphasia. These variables are readily available or easily obtained and the regression model reported may be useful for estimating confrontation naming item difficulty without the need for collection of response data from large samples of people with aphasia.

Dataset Information

Predicting Spatial Visualization Problems' Difficulty Level from Eye-Tracking Data.

Publications

Predicting Spatial Visualization Problems' Difficulty Level from Eye-Tracking Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets