Use Of Eye Tracking Data Research Articles

Product Recommendation Based on Eye Tracking Data Using Fixation Duration

E-commerce can be used to increase companies or sellers’ profits. For consumers, e-commerce can help them shop faster. The weakness of e-commerce is that there is too much product information presented in the catalog which in turn makes consumers confused. The solution is by providing product recommendations. As the development of sensor technology, eye tracker can capture user attention when shopping. The user attention was used as data of consumer interest in the product in the form of fixation duration following the Bojko taxonomy. The fixation duration data was processed into product purchase prediction data to know consumers’ desire to buy the products by using Chandon method. Both data could be used as variables to make product recommendations based on eye tracking data. The implementation of the product recommendations based on eye tracking data was an eye tracking experiment at selvahouse.com which sells hijab and women modest wear. The result was a list of products that have similarities to other products. The product recommendation method used was item-to-item collaborative filtering. The novelty of this research is the use of eye tracking data, namely the fixation duration and product purchase prediction data as variables for product recommendations. Product recommendation that produced by eye tracking data can be solution of product recommendation’s problems, namely sparsity and cold start.

Four-class emotion classification in virtual reality using pupillometry

BackgroundEmotion classification remains a challenging problem in affective computing. The large majority of emotion classification studies rely on electroencephalography (EEG) and/or electrocardiography (ECG) signals and only classifies the emotions into two or three classes. Moreover, the stimuli used in most emotion classification studies utilize either music or visual stimuli that are presented through conventional displays such as computer display screens or television screens. This study reports on a novel approach to recognizing emotions using pupillometry alone in the form of pupil diameter data to classify emotions into four distinct classes according to Russell’s Circumplex Model of Emotions, utilizing emotional stimuli that are presented in a virtual reality (VR) environment. The stimuli used in this experiment are 360° videos presented using a VR headset. Using an eye-tracker, pupil diameter is acquired as the sole classification feature. Three classifiers were used for the emotion classification which are Support Vector Machine (SVM), k-Nearest Neighbor (KNN), and Random Forest (RF).FindingsSVM achieved the best performance for the four-class intra-subject classification task at an average of 57.05% accuracy, which is more than twice the accuracy of a random classifier. Although the accuracy can still be significantly improved, this study reports on the first systematic study on the use of eye-tracking data alone without any other supplementary sensor modalities to perform human emotion classification and demonstrates that even with a single feature of pupil diameter alone, emotions could be classified into four distinct classes to a certain level of accuracy. Moreover, the best performance for recognizing a particular class was 70.83%, which was achieved by the KNN classifier for Quadrant 3 emotions.ConclusionThis study presents the first systematic investigation on the use of pupillometry as the sole feature to classify emotions into four distinct classes using VR stimuli. The ability to conduct emotion classification using pupil data alone represents a promising new approach to affective computing as new applications could be developed using readily-available webcams on laptops and other mobile devices that are equipped with cameras without the need for specialized and costly equipment such as EEG and/or ECG as the sensor modality.

SteadEye-Head-Improving MARG-Sensor Based Head Orientation Measurements Through Eye Tracking Data.

This paper presents the use of eye tracking data in Magnetic AngularRate Gravity (MARG)-sensor based head orientation estimation. The approach presented here can be deployed in any motion measurement that includes MARG and eye tracking sensors (e.g., rehabilitation robotics or medical diagnostics). The challenge in these mostly indoor applications is the presence of magnetic field disturbances at the location of the MARG-sensor. In this work, eye tracking data (visual fixations) are used to enable zero orientation change updates in the MARG-sensor data fusion chain. The approach is based on a MARG-sensor data fusion filter, an online visual fixation detection algorithm as well as a dynamic angular rate threshold estimation for low latency and adaptive head motion noise parameterization. In this work we use an adaptation of Madgwicks gradient descent filter for MARG-sensor data fusion, but the approach could be used with any other data fusion process. The presented approach does not rely on additional stationary or local environmental references and is therefore self-contained. The proposed system is benchmarked against a Qualisys motion capture system, a gold standard in human motion analysis, showing improved heading accuracy for the MARG-sensor data fusion up to a factor of 0.5 while magnetic disturbance is present.

Non-Intrusive Detection of Drowsy Driving Based on Eye Tracking Data

Drowsy driving is one of the leading causes of motor vehicle accidents in North America. This paper presents the use of eye tracking data as a non-intrusive measure of driver behavior for detection of drowsiness. Eye tracking data were acquired from 53 subjects in a simulated driving experiment, whereas the simultaneously recorded multichannel electroencephalogram (EEG) signals were used as the baseline. A random forest (RF) and a non-linear support vector machine (SVM) were employed for binary classification of the state of vigilance. Different lengths of eye tracking epoch were selected for feature extraction, and the performance of each classifier was investigated for every epoch length. Results revealed a high accuracy for the RF classifier in the range of 88.37% to 91.18% across all epoch lengths, outperforming the SVM with 77.12% to 82.62% accuracy. A feature analysis approach was presented and top eye tracking features for drowsiness detection were identified. Altogether, this study showed a high correspondence between the extracted eye tracking features and EEG as a physiological measure of vigilance and verified the potential of these features along with a proper classification technique, such as the RF, for non-intrusive long-term assessment of drowsiness in drivers. This research would ultimately lead to development of technologies for real-time assessment of the state of vigilance, providing early warning of fatigue and drowsiness in drivers.

Positive vs. Negative Framing of Scientific Information on Facebook Using Peripheral Cues: An Eye-Tracking Study of the Credibility Assessment Process

Aim/Purpose: To examine how positive/negative message framing – based on peripheral cues (regarding popularity, source, visuals, and hyperlink) – affects perceptions of credibility of scientific information posted on social networking sites (in this case, Facebook), while exploring the mechanisms of viewing the different components. Background: Credibility assessment of information is a key skill in today's information society. However, it is a demanding cognitive task, which is impossible to perform for every piece of online information. Additionally, message framing — that is, the context and approach used to construct information— may impact perceptions of credibility. In practice, people rely on various cues and cognitive heuristics to determine whether they think a piece of content is true or not. In social networking sites, content is usually enriched by additional information (e.g., popularity), which may impact the users' perceived credibility of the content. Methodology: A quantitative controlled experiment was designed (N=19 undergraduate students), collecting fine grained data with an eye tracking camera, while analyzing it using transition graphs. Contribution: The findings on the mechanisms of that process, enabled by the use of eye tracking data, point to the different roles of specific peripheral cues, when the message is overall peripherally positive or negative. It also contributes to the theoretical literature on framing effects in science communication, as it highlights the peripheral cues that make a strong frame. Findings: The positively framed status was perceived, as expected from the Elaboration Likelihood Model, more credible than the negatively framed status, demonstrating the effects of the visual framing. Differences in participants' mechanisms of assessing credibility between the two scenarios were evident in the specific ways the participants examined the various status components. Recommendations for Practitioners: As part of digital literacy education, major focus should be given to the role of peripheral cues on credibility assessment in social networking sites. Educators should emphasize the mechanisms by which these cues interact with message framing, so Internet users would be encouraged to reflect upon their own credibility assessment skills, and eventually improve them. Recommendation for Researchers: The use of eye tracking data may help in collecting and analyzing fine grained data on credibility assessment processes, and on Internet behavior at large. The data shown here may shed new light on previously studied phenomena, enabling a more nuanced understanding of them. Impact on Society: In an era when Internet users are flooded with information that can be created by virtually anyone, credibility assessment skills have become ever more important, hence the prominence of this skill. Improving citizens' assessment of information credibility — to which we believe this study contributes — results on a greater impact on society. Future Research: The role of peripheral cues and of message framing should be studied in other contexts (not just scientific news) and in other platforms. Additional peripheral cues not tested here should be also taken into consideration (e.g., connections between the information consumer and the information sharer, or the type of the leading image).

Visual Attention Distribution Based Assessment of User's Skill in Electronic Medical Record Navigation

Currently, the most precise way of reflecting the skills level is an expert’s subjective assessment. In this paper we investigate the possibility of the use of eye tracking data for scalar quantitative and objective assessment of medical staff competency in EMR system navigation. According to the experiment conducted by Yarbus the observation process of particular features is associated with thinking. Moreover, eye tracking is proved to clarify the relationships between eye movements, visual attention and insight to the complex task performance. Using the similarities between the reference attention map and the one recorded for the assessed person, as well as the total time of the performance, we have proposed the Visual Attention Time Product (VATP) to distinguish the level of knowledge and familiarity with EMR systems. We used Spearman Rank to compare the obtained VATP scores with the 5-point scale expert’s assessment about the test participants’ performance. The VATP was also compared with the other methods used for classification of the competency test results (attention, similarities and time). Twenty-five people with completed basic training in the EMR usage participated in the proposed experiment. The proposed VATP, calculated with regards to the reference performance of the exemplary expert, shows very strong correlation (0, 92) with the expert’s assessment of the observed performance in solving EMR related tasks. The VATP was also calculated regarding the average performance of all experts who participated in the experiment. Again the results show strong correlation (0, 90). Moreover, the results show that the eye tracking interface does not influence on the EMR navigation. We demonstrate that the eye tracking data and proposed VATP can be successfully used to differentiate the level of performance in EMR system related tasks. It also appeared that the parameter VATP enables the assessment of the examinee comparable to that performed by expert. The level of complexity of the computation allows the gathering of results directly after the conducted test. Thus, the VATP can be successfully used for EMR end user skills differentiation and competency testing.

Economic Insights from “Neuroeconomic” Data

How and to what extent “neuroeconomic” data (broadly interpreted as data other than standard choice data) should be used in advancing economic theory is open to question. Several authors have attempted to make use of such nonstandard data to shed light on the process of economic decision making. John W. Payne, James R. Bettman, and Eric. J. Johnson (1993), Miguel Costa Gomes, Vincent P. Crawford, and Bruno Broseta (2001), and Xavier Gabaix et al. (2006) have used MouseLab software in order to determine the manner in which people use information. Joseph Wang, Michael Spezio, and Colin Camerer (2006) make use of eye-tracking data for the same purpose. More dramatically, researchers such as Paul William Glimcher, Joseph Kable, and Kenway Louie (2007) are using brain-scanning data in an attempt to constrain economic models of discounting and time preference. Camerer (forthcoming) presents an excellent review of economic research involving nonstandard data. In opposition to this trend, Faruk Gul and Wolfgang Pesendorfer (forthcoming) present a strong critique of the use of nonchoice data within economics. They put forward two specific arguments that users of “neuroeconomic” data must refute if their work is to be taken seriously. First—economic models were designed only to explain choices. Thus, nonchoice data can be used neither to confirm nor deny a particular economic model. Second, it is by and large true that economists are interested in choice behavior. Any two models will either make different predictions for choice, in which case they can be differentiated by standard choice data, or they will not, in which case an economist will not be interested in differentiating between them. Economic Insights from “Neuroeconomic” Data

眼球運動解析に基づく視聴覚情報を考慮したテレビ広告認知の分析

眼球運動解析に基づく視聴覚情報を考慮したテレビ広告認知の分析

Using Eye-Tracking Video Data to Augment Knowledge Elicitation in Cognitive Task Analysis

Cognitive task analysis (CTA) is a process to determine cognitive activities required to accomplish a given task. Different methods have been proposed and advocated in performing CTA. In this paper, we report a pilot trial using eye-tracking data to facilitate CTA. A mobile eye-tracking device was used in surgical operating rooms to acquire eye-tracking data from an operator during a highly complex, taxing procedure: tracheal intubation. A desktop task analysis was performed to establish visual cues and their associated goals during tracheal intubation. Eye tracking data were reviewed by Subject Matter Experts (SMEs) as memory recall cues. The advantage of such use of eye tracking data was that the SMEs did not have to provide frame-by-frame analysis of the fixations, since they provided speculation on fixations and mental processes, cued by the eye tracking data. Pilot trials showed the value of eye tracking data in CTA in terms of knowledge elicitation. Future exploration of such methodology is highly suggested given the increasing feasibility of deploying eye-tracking devices.