The Application of Artificial Intelligence to Automate Sensory Assessments Combining Pretrained Transformers with Word Embedding Based on the Online Sensory Marketing Index

We present how artificial intelligence (AI)-based technologies create new opportunities to capture and assess sensory marketing elements. Based on the Online Sensory Marketing Index (OSMI), a assessment framework designed evaluate e-commerce websites manually, goal is offer an alternative procedure elements such as text images automatically. This approach aims provide managers with valuable insights potential for improvements. To accomplish task, we initially reviewed 469 related peer-reviewed scientific publications. In this process, manual reading complemented by validated AI methodology. identify relevant topics check if they exhibit comprehensible distribution over last years. recognize discuss similar approaches from machine learning big data environment. apply state-of-the-art methods natural language processing domain principal analysis, word embedding techniques GloVe Word2Vec, leverage transformers BERT. validate performance of our newly developed approach, compare results manually collected parameters previous studies observe findings in both procedures. Our reveal functional scalable determining OSMI industries, companies, or even individual (sub-) websites. addition, selection procedures are extremely fast, only small loss compared evaluation. It resembles efficient way efforts.