scholarly journals Effects of individuality, education, and image on visual attention: Analyzing eye-tracking data using machine learning

2019 ◽  
Vol 12 (2) ◽  
Author(s):  
Sangwon Lee ◽  
Yongha Hwang ◽  
Yan Jin ◽  
Sihyeong Ahn ◽  
Jaewan Park
Keyword(s):  
Machine Learning ◽  
Visual Attention ◽  
Eye Tracking ◽  
Mathematical Models ◽  
Classification Algorithms ◽  
Tracking Data ◽  
The Impact

Machine learning, particularly classification algorithms, constructs mathematical models from labeled data that can predict labels for new data. Using its capability to identify distinguishing patterns among multi-dimensional data, we investigated the impact of three factors on the observation of architectural scenes: Individuality, education, and image stimuli. An analysis of the eye-tracking data revealed that (1) a velocity histogram was unique to individuals, (2) students of architecture and other disciplines could be distinguished via endogenous parameters, but (3) they were more distinct in terms of seeking structural versus symbolic elements. Because of the reverse nature of the classification algorithms that automatically learn from data, we could identify relevant parameters and distinguishing eye-tracking patterns that have not been reported in previous studies.

scholarly journals Are Photographs Worth More Than a Thousand Words? Examining the Effects of Photographic–Textual and Textual-Only Frames on Public Attitude Toward Nuclear Energy and Nanotechnology

2018 ◽  
Vol 95 (4) ◽  
pp. 948-970 ◽  
Author(s):  
Edmund W. J. Lee ◽  
Shirley S. Ho
Keyword(s):  
Risk Perception ◽  
Visual Attention ◽  
Eye Tracking ◽  
Nuclear Energy ◽  
Public Support ◽  
Public Attitude ◽  
Theory And Practice ◽  
Tracking Data ◽  
Subject Design ◽  
The Impact

This study examines the impact of photographic–textual and risk–benefit frames on the level of visual attention, risk perception, and public support for nuclear energy and nanotechnology in Singapore. Using a 2 (photographic–textual vs. textual-only frames) × 2 (risk vs. benefit frames) × 2 (nuclear energy vs. nanotechnology) between-subject design with eye-tracking data, the results showed that photographic–textual frames elicited more attention and did have partial amplification effect. However, this was observable only in the context of nuclear energy, where public support was lowest when participants were exposed to risk frames accompanied by photographs. Implications for theory and practice were discussed.

scholarly journals Nutri-Score and Nutrition Facts Panel through the Eyes of the Consumer: Correct Healthfulness Estimations Depend on Transparent Labels, Fixation Duration, and Product Equivocality

Nutrients ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2915
Author(s):  
Saar Bossuyt ◽  
Kathleen Custers ◽  
José Tummers ◽  
Laura Verbeyst ◽  
Bert Oben
Keyword(s):  
Visual Attention ◽  
Eye Tracking ◽  
Fixation Duration ◽  
Positive Impact ◽  
Estimation Accuracy ◽  
Tracking Data ◽  
Negative Effect ◽  
Set Up ◽  
Nutrition Facts Panel ◽  
The Impact

Research on front-of-pack labels (FOPLs) demonstrated that Nutri-Score is one of the most promising FOPLs regarding healthfulness estimation accuracy. Nevertheless, as consumers are exposed to both the Nutri-Score and the mandatory Nutrition Facts Panel (NFP) in the supermarket, it is key to understand if and how both labels interact. This study investigates the contribution of Nutri-Score and NFP regarding healthfulness estimation accuracy, whether this impact differs depending on the product, and what role visual attention plays. We set up an eye-tracking experiment in a controlled setting in which 398 participants rated the healthfulness of 20 products. The results confirmed the positive impact of the Nutri-Score on healthfulness estimation accuracy, though the impact was larger for equivocal (i.e., difficult to judge) products. Interestingly, NFP either had no effect (compared to a package without Nutri-Score or NFP) or a negative effect (compared to a package with Nutri-Score alone) on healthfulness estimation accuracy. Eye-tracking data corroborated that ‘cognitive overload’ issues could explain why consumers exposed to Nutri-Score alone outperformed those exposed to both Nutri-Score and NFP. This study offers food for thought for policymakers and the industry seeking to maximize the potential of the Nutri-Score.

scholarly journals Fixation classification: how to merge and select fixation candidates

2022 ◽  
Author(s):  
Ignace T. C. Hooge ◽  
Diederick C. Niehorster ◽  
Marcus Nyström ◽  
Richard Andersson ◽  
Roy S. Hessels
Keyword(s):  
Eye Tracking ◽  
Marketing Research ◽  
Classification Algorithms ◽  
Extensive Literature ◽  
Tracking Data ◽  
Selection Rules ◽  
The Gaze ◽  
Research Fields ◽  
Fixation Durations ◽  
The Impact

AbstractEye trackers are applied in many research fields (e.g., cognitive science, medicine, marketing research). To give meaning to the eye-tracking data, researchers have a broad choice of classification methods to extract various behaviors (e.g., saccade, blink, fixation) from the gaze signal. There is extensive literature about the different classification algorithms. Surprisingly, not much is known about the effect of fixation and saccade selection rules that are usually (implicitly) applied. We want to answer the following question: What is the impact of the selection-rule parameters (minimal saccade amplitude and minimal fixation duration) on the distribution of fixation durations? To answer this question, we used eye-tracking data with high and low quality and seven different classification algorithms. We conclude that selection rules play an important role in merging and selecting fixation candidates. For eye-tracking data with good-to-moderate precision (RMSD < 0.5∘), the classification algorithm of choice does not matter too much as long as it is sensitive enough and is followed by a rule that selects saccades with amplitudes larger than 1.0∘ and a rule that selects fixations with duration longer than 60 ms. Because of the importance of selection, researchers should always report whether they performed selection and the values of their parameters.

scholarly journals Understanding the role of visual attention on wines’ purchase intention: an eye-tracking study

2019 ◽  
Vol 32 (2) ◽  
pp. 161-179
Author(s):  
Patrícia Monteiro ◽  
João Guerreiro ◽  
Sandra Maria Correia Loureiro
Keyword(s):  
Visual Attention ◽  
Eye Tracking ◽  
Purchase Intention ◽  
Purchase Intentions ◽  
Monitoring Method ◽  
Content Type ◽  
Quality Perceptions ◽  
Consumption Situation ◽  
The Impact

Purpose Wine bottles compete for consumers’ attention in the shelf during the decisive moment of choice. This study aims to explore the role that visual attention to wine labels has on the purchase decision and the mediating role of quality perceptions and desire on such purchase behaviours. Wine awards and consumption situation are used as moderators.. Design/methodology/approach The study was conducted in Portugal and 36 individuals participated in a 2 × 2 within subjects design (awarded/not awarded × self-consumption/social-consumption). For each scenario, individuals’ attention, perceptions of quality, desire and purchase intentions were recorded. Findings Data from eye-tracking shows that, during the purchase process, the amount of attention given to a bottle is determinant of individuals’ purchase intentions, a relationship that increases in significance for bottles with awards and for when consumers are buying wine for a consumption situation involving a social environment. In addition, both quality perceptions and desire are confirmed to positively influence wines’ purchase intentions. Originality/value By using an eye monitoring method, this paper brings new insights into the wine industry by highlighting the impact that wines’ labels and different consumption situations have on individuals’ attention and purchase intention. Wine producers and retailers may benefit from the insights provided by the current study to refine their communication strategies by either highlighting product characteristics and pictorial elements, as it is the case of the awards, or communicating about their products for different consumption situations.

scholarly journals Correction to: “Using machine learning to detect events in eye-tracking data”

2018 ◽  
Vol 51 (1) ◽  
pp. 451-452
Author(s):  
Raimondas Zemblys ◽  
Diederick C. Niehorster ◽  
Kenneth Holmqvist
Keyword(s):  
Machine Learning ◽  
Eye Tracking ◽  
Tracking Data

scholarly journals How the fear of COVID-19 changed the way we look at human faces

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e11380
Author(s):  
Giovanni Federico ◽  
Donatella Ferrante ◽  
Francesco Marcatto ◽  
Maria Antonella Brandimonte
Keyword(s):  
Social Interaction ◽  
Visual Attention ◽  
Eye Tracking ◽  
Perceived Risk ◽  
Human Faces ◽  
The Impact ◽  
Basic Level ◽  
The Way

Do we look at persons currently or previously affected by COVID-19 the same way as we do with healthy ones? In this eye-tracking study, we investigated how participants (N = 54) looked at faces of individuals presented as “COVID-19 Free”, “Sick with COVID-19”, or “Recovered from COVID-19”. Results showed that participants tend to look at the eyes of COVID-19-free faces longer than at those of both COVID-19-related faces. Crucially, we also found an increase of visual attention for the mouth of the COVID-19-related faces, possibly due to the threatening characterisation of such area as a transmission vehicle for SARS-CoV-2. Thus, by detailing how people dynamically changed the way of looking at faces as a function of the perceived risk of contagion, we provide the first evidence in the literature about the impact of the pandemic on the most basic level of social interaction.

scholarly journals Predicting Spatial Visualization Problems’ Difficulty Level from Eye-Tracking Data

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1949
Author(s):  
Xiang Li ◽  
Rabih Younes ◽  
Diana Bairaktarova ◽  
Qi Guo
Keyword(s):  
Machine Learning ◽  
Eye Tracking ◽  
Eye Movement ◽  
Spatial Visualization ◽  
Difficulty Level ◽  
Tracking Data ◽  
Multiple Choice Questions ◽  
Essential Information ◽  
E Learning ◽  
The Difference

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.

Sign in / Sign up

Export Citation Format

Share Document