Quantifying the Relationships between Everyday Objects and Emotional States through Deep ...
summary
Built an Android logging system called MyMood app that collects ESM mood entries with photos and 7‑point Likert scores, runs deep learning object detection on images, and analyzes associations across 3,305 mood reports from 22 participants (Sep 2018–Oct 2019). Findings show indoor objects (keyboard, laptop) dominate, work-related objects associate with higher stress while home objects link to lower stress, outdoor objects correlate with greater activeness, valence associations are weak, and object–mood links strengthen when conditioned on location.
AI-written summary · about
chapters (3)
related talks
11mAmbient Intelligence and Emotionally Intelligent Devices
07mMultimodal Emotion Recognition of Hand-Object Interaction
19mInTheMoodForLife: Analyzing Sleep to Better Manage Mood Disorders
49mAffective Computing – Bringing Humans and Machines Closer Through Emotions
10mVEmotion: Using Driving Context for Indirect Emotion Prediction in Real-Time
34mEnhancing Customer Experiences with Emotional AI,
06mPerson-Centered Predictions of Psychological Constructs with Social Media Contextualized by ...
06mDetecting Stressful Social Interactions Using Wearable Physiological and Inertial Sensors