- Civit Masot, Javier
- Luna Perejón, Francisco
- Muñoz Saavedra, Luis
- Civit Masot, Miguel
- Domínguez Morales, Manuel Jesús
- Miró Amarante, María Lourdes
The PaGER-Sync ADICVIDEO dataset is a multimodal, temporally synchronized repository of physiological and facial expression data recorded during controlled, immersive video game sessions designed to simulate realistic home gaming environments. It integrates biosignals from the Empatica E4 wristband —including Electrodermal Activity (EDA), Blood Volume Pulse (BVP), and Skin Temperature (TEMP) — with facial expression features extracted from video recordings using FaceReader software. Additionally, the dataset includes scores from pre-session psychometric questionnaires (Gaming Addiction Scale, Scale of Positive and Negative Experience, Emotion Regulation Questionnaire) and demographic gender data, providing psychological and individual difference context. A summary file detailing the two strongest emotions expressed by each participant with their respective percentages is included. A total of 25 participants played three commercial video games (Tetris, Sonic Racing, and Fall Guys) under controlled conditions, while their physiological responses were continuously recorded and their facial expressions captured on video for subsequent analysis. All data streams were precisely aligned using a common video-based timestamp, enabling frame-level synchronization across modalities, and the data were segmented by game. The dataset supports a wide range of research applications in affective computing, human-computer interaction, and behavioral analysis, and is particularly well-suited for the development and evaluation of multimodal affect detection models, as well as for exploring the interplay between psychological traits and real-time emotional responses., The PaGER-Sync dataset is meticulously organized into .xlsx spreadsheet files, structured to facilitate both general overview and detailed per-participant and per-trial analysis. Raw video recordings of participants are not provided due to privacy restrictions stipulated by the ethical committee approval.
The dataset comprises the following key components:
_Video_datetime_UTC.xlsx: A global file providing session-level metadata for all trials:
Participant: An anonymous ID consisting of two letters and three numbers, self-assigned.
Trial: A numerical identifier for each specific gameplay session.
Game: A unique identifier for the video game played in that session (values: "Tetris", "Sonic", "FallG" for Fall Guys).
Video_UTC_dateTime: Exact UTC start timestamp of the video recording (DD/MM/YYYY HH:MM:SS). This timestamp serves as a reference for synchronizing all modalities.
Raw Physiological Data Files (per Participant): For each participant, separate .xlsx files contain the raw, unsynchronized values of their physiological signals across all their trials. These files include:
Participant_eda.xlsx: Electrodermal Activity (EDA) values with corresponding UTC timestamps
Participant_bvp.xlsx: Blood Volume Pulse (BVP) readings with UTC timestamps.
Participant_temp.xlsx: Skin Temperature (TEMP) measurements with UTC timestamps.
Synchronized Emotion Video Data Files (per Trial): For each individual trial (gameplay session) of a participant, a comprehensive Participant_Trial_Video_Data.xlsx file is generated. This file represents the core of the synchronized dataset, containing:
Timestamp: Seconds from the start of the video recording.
State: Dominant emotion classified by FaceReader 9.1 (e.g., "Happy", "Sad", "Neutral"), validated by expert review.
Valence and Arousal: Continuous numerical scores.
Facial Action Units (AUs): Intensity values for the 18 specific Action Units detected by OpenFace 2.2, at 20 FPS.
_Emotions_Summary.xlsx:
Participant (Alphanumeric): An anonymous ID consisting of two letters and three numbers, self-assigned, allowing this file to be linked with existing multimodal data.
Emotion_1 (Categorical): The most dominant or frequently expressed emotion by the participant throughout their gaming sessions, according to FaceReader analysis.
Emotion_1_Ratio (Numeric): The percentage of time or intensity with which Top_Emotion_1 was expressed for that participant.
Emotion_2 (Categorical): The second most dominant or frequently expressed emotion by the participant.
Emotion_2_Ratio (Numeric): The percentage of time or intensity with which Top_Emotion_2 was expressed for that participant.
_Psychometric and Demographic Data.xlsx:
Participant (Alphanumeric): An anonymous ID consisting of two letters and three numbers, self-assigned, allowing this file to be linked with existing multimodal data.
Gender (Categorical): Self-reported gender of the participant (Male or Female).
GASA_Total_Score (Numeric): Total score from the Gaming Addiction Scale (GAS), a 7-item questionnaire assessing problematic video game use.
GASA_Problematic_Use_Indicator (Binary): Binary indicator (0 or 1) derived from the GAS score, where 1 typically denotes problematic or addictive use (a score of 3 or higher on at least four items).
SPANE_Positive_Affect_Score (Numeric): Score from the Positive Affect subscale of the Scale of Positive and Negative Experience (SPANE-P), measuring the frequency of positive feelings. Range: 6 to 30.
SPANE_Negative_Affect_Score (Numeric): Score from the Negative Affect subscale of the Scale of Positive and Negative Experience (SPANE-N), measuring the frequency of negative feelings. Range: 6 to 30.
SPANE_Affect_Balance_Score (Numeric): Score from the Affect Balance subscale of the Scale of Positive and Negative Experience (SPANE-B), calculated as SPANE-P minus SPANE-N. Range: -24 to 24
ERQ_Cognitive_Reappraisal_Score (Numeric): Score from the Cognitive Reappraisal subscale of the Emotion Regulation Questionnaire (ERQ), measuring the tendency to change one's thinking about a situation to regulate emotions
ERQ_Expressive_Suppression_Score (Numeric): Score from the Expressive Suppression subscale of the Emotion Regulation Questionnaire (ERQ), measuring the tendency to inhibit the behavioral expression of emotions.