machine learning-based visual art recommendation system  (CH Instruments)

Journal: Frontiers in Psychology

Article Title: Art psychotherapy meets creative AI: an integrative review positioning the role of creative AI in art therapy process

doi: 10.3389/fpsyg.2025.1548396

Figure Lengend Snippet: Characteristics of included papers, conceptualisation of art therapy (AI) and creative artificial intelligence (AI), and indicated role of creative AI in AT.

Article Snippet: (9) Luxembourg / Netherlands / Canada , Conference proceedings: CHI Conference on Human Factors in Computing Systems (CHI’24), Honolulu, USA , To investigate the potential of Machine Learning (ML) based Visual Art Recommendation System (VA RecSys) “to enable personalized therapeutic visual art experiences for post-ICU patients” , IP: patients with post-intensive care syndrome (PICS) M1: development study with usability testing, interviews P1: 4 experts: ICU nurses, healthcare and affective design researchers M2: pre-post study (guided AT session): reflexive thematic & sentiment analyses, psychometric testing P2: 150 post-COVID patients from UK, USA and South Africa , Medium-high: peer-review process unclear, methods clearly described, sound analysis and implications for practice , - AT “as an umbrella term where art serves as a medium for therapeutic benefits,” including “engaging with existing artwork to stimulate emotions and self-reflections” and “use of visual art as a positive distraction” (i.e., [art] exposure therapy) , - Machine Learning-based Visual Art Reccommendation System (ML-based VA RecSys): “personalisation of healing art for therapeutic purposes” - Proposing “personalized guided art therapy”: choosing preferred artworks from sample paintings, followed by AI recommending artworks and “asking questions that encourage participants to engage with the paintings,” and finally reflecting on the experience , - To “improve temporary stress and evoke positive emotions” for post-ICU patients - “A careful selection of paintings tailored to the individual patient speaks to their unique circumstances, fostering self-reflection and healing,” AI “can bridge the gap between the vast universe of artworks and the unique emotional needs of each patient” - Themes (“healing elements”) identified: hope and purpose, rejuvenation, engagement, safety, sensory pleasure, relevance, personal preference.

Techniques: Software, Expressing, Selection