Fatma Semira Yıldırım

Ms. Fatma Semira Yıldırım


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 August 2025 in Information Technology & Tourism
Verified
Journal Article
Closed access
PDF file
ESErdem Savaşcı
Erdem Savaşcı
FYFatma Semira Yıldırım
Fatma Semira Yıldırım
SSSelay Ilgaz Sümer
Selay Ilgaz Sümer
ESEmre Sümer
Emre Sümer

Verified
Journal Article
Open access
PDF file
SSSeda Busra Sarac
Seda Busra Sarac
KAKazim Baris Atici
Kazim Baris Atici
IBIsmail Bezci
Ismail Bezci
ADAta Erinç Dansuk
Ata Erinç Dansuk
FYFatma Semira Yıldırım
Fatma Semira Yıldırım
This study aims to provide insight into consumer purchasing decisions by integrating eye-tracking data with forecasting techniques. First, the study investigates how consumption motives (hedonic vs. utilitarian) and purchasing purposes (for oneself vs. for others) influence visual attention and decision-making processes. An experimental design was conducted with 128 participants in a simulated online shopping environment, where eye-tracking data were collected based on fixation counts and durations across defined Areas of Interest (AOIs). Second, a total of 20 input features were collected, comprising fixation counts and fixation durations for 10 review-related Areas of Interest (AOIs), and these features were evaluated across the experimental scenarios, while the binary output variable represented the participant’s purchase decision. These biometric features, together with scenario information, were used to forecast purchasing decisions using six machine-learning methods, including Artificial Neural Networks, Random Forest, Support Vector Machine, K-Nearest Neighbors, Naive Bayes, and Logistic Regression. The results indicate that consumers’ visual attention aligns with their consumption motives and purchasing purposes, revealing distinct gaze patterns across different scenarios. In the forecasting phase, the accuracy of different methods for predicting purchasing decisions using review-related eye-tracking data is evaluated. Support Vector Machines achieved the highest overall accuracy, approximately 59–60% across the evaluated datasets, compared with a validation-specific majority-class baseline of 53.85%. This corresponds to a modest improvement of approximately 5.15–6.15 percentage points over the naive benchmark. Overall, the findings suggest that objectively recorded review-related eye-tracking data can be operationalized as behavioral input features in a machine-learning-based purchase-decision classification framework, highlighting the methodological value of integrating eye-tracking insights with consumer behavior forecasting.