[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128184-en":3,"doc-seo-128184-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128184,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","What Makes an Ad Memorable - A Multimodal Machine Learning Study in Neuromarketing","Advertising brand recall is a key indicator of ad effectiveness, yet traditional self-reported approaches struggle to capture the unconscious mechanisms behind memory formation. This thesis proposes a multimodal neuromarketing framework that combines biometric signals—EEG and galvanic skin response (GSR)—with extracted audiovisual features to predict unaided brand recall. Using a large experiment with 600 participants across viewing conditions, deep learning and machine learning models are evaluated, and interpretable mediation via path modelling is performed.","What Makes an Ad Memorable? A Multimodal Machine Learning Study in Neuromarketing  \nMaster of Science Thesis in  \nManagement Engineering  \nAuthors:  \nAlessio Cerboni  \nLuca Panti  \nStudent ID: 10934057; 10707591  \nSupervisor: Prof. Lucio Lamberti  \nCo-supervisors: Marc-Antoine Fortin  \nAcademic Year: 2023-2024  \ni  \nAbstract  \nAdvertising brand recall is a critical measure of advertisement effectiveness, yet traditional self-reported methods often fail to capture the subconscious processes that lead to memory formation. This thesis introduces a multimodal approach that integrates biometric signals, specifically electroencephalogram (EEG) and galvanic skin response (GSR) with extracted audiovisual features to predict unaided brand recall in advertising contexts. In a large-scale experiment involving 600 participants exposed to advertisements under various viewing conditions (simulated linear TV and on-demand platforms), physiological data and ad content metrics were collected and analysed using both deep learning (CNNLSTM architectures) and machine learning (e.g., XGBoost, SVM) techniques. The results demonstrate that multimodal integration increases recall prediction accuracy compared to unimodal approaches. Moreover, logistic regression was considered to retrieve linear and interpretable patterns, rather than focusing solely on prediction accuracy. Specifically, neural markers such as beta oscillations positively correlate with recall, whereas alpha and gamma oscillations show negative associations. Another notable finding shows the significance of audio-visual features like colour, motion and audio respect to unaided recall. Eventually, path modelling reveals that beta wave responses mediate the impact of some audiovisual features on recall. These findings advance our understanding of the relationships between external stimuli and internal cognitive processes and provide actionable insights for designing more effective advertising strategies.  \nKeywords: advertising recall; neuromarketing; biometric signals; eeg; machine learning; multimodal; audiovisual; path modelling.  \niii  \nSommario  \nIl richiamo del brand nelle pubblicità è una misura fondamentale dell’efficacia pubblicitaria, ma i metodi tradizionali basati ad esempio su questionari o focus groups, spesso non riescono a catturare i processi inconsci che portano alla formazione della memoria. Questo studio introduce un approccio multimodale che integra segnali biometrici, in particolare Elettroencefalografo (EEG) e Galvanic Skin Response (GSR), con caratteristiche audiovisive estratte per prevedere il richiamo del brand. In un esperimento con 600 partecipanti esposti a pubblicità in diverse condizioni di fruizione (TV lineare e piattaformeon-demand), sono stati raccolti e analizzati dati fisiologici e metriche relative ai contenuti pubblicitari utilizzando sia tecniche di deep learning (architetture CNN-LSTM) sia metodi di machine learning (ad esempio, XGBoost, SVM) . I risultati dimostrano chel’integrazione multimodale aumenta l’accuratezza della previsione del richiamo rispettoagli approcci unimodali. Inoltre, è stata considerata la regressione logistica per individuareschemi lineari e interpretabili, piuttosto che concentrarsi esclusivamente sulla precisionepredittiva. In particolare, si osserva che le variabili biometriche, come le onde beta, sono positivamente correlati al richiamo, mentre le oscillazioni alfa e gamma mostrano associazioni negative. Un altro risultato rilevante evidenzia l’importanza di caratteristiche audiovisive come colore, dinamicità e audio rispetto al richiamo. Infine, la path analysis rivela che le onde beta mediano l’impatto di alcune caratteristiche audiovisive sul richiamo. Questi risultati avanzano la comprensione delle relazioni tra stimoli esterni eprocessi cognitivi interni, offrendo spunti concreti per progettare strategie di marketing più efficaci.  \nParole chiave: richiamo della pubblicità; neuromarketing; segnali biometrici; eeg;","cbCaiidpL22KfW7s","https://ap.wps.com/l/cbCaiidpL22KfW7s","pdf",3548532,4,1,162,"English","en",105,"# Abstract\n## Objectives\n## Research Questions","[{\"question\":\"How does the study measure advertising effectiveness?\",\"answer\":\"It focuses on advertising brand recall, specifically unaided brand recall, as the primary measure of effectiveness.\"},{\"question\":\"What data inputs are used to predict unaided brand recall?\",\"answer\":\"The model integrates biometric signals (EEG and GSR) together with audiovisual advertisement features such as color, motion, and audio-related characteristics.\"},{\"question\":\"Which modelling approaches does the thesis use?\",\"answer\":\"It compares deep learning architectures (e.g., CNN-LSTM) and machine learning methods (e.g., XGBoost, SVM) and also considers logistic regression for interpretable linear patterns.\"}]","What Makes an Ad Memorable - A Multimodal Machine Learning Study in Neuromarketing | PDF",1785945341,408,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"what-makes-an-ad-memorable-a-multimodal-machine-learning-study-in-neuromarketing","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/what-makes-an-ad-memorable-a-multimodal-machine-learning-study-in-neuromarketing/128184/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"How does the study measure advertising effectiveness?","Question",{"text":76,"@type":77},"It focuses on advertising brand recall, specifically unaided brand recall, as the primary measure of effectiveness.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What data inputs are used to predict unaided brand recall?",{"text":81,"@type":77},"The model integrates biometric signals (EEG and GSR) together with audiovisual advertisement features such as color, motion, and audio-related characteristics.",{"name":83,"@type":74,"acceptedAnswer":84},"Which modelling approaches does the thesis use?",{"text":85,"@type":77},"It compares deep learning architectures (e.g., CNN-LSTM) and machine learning methods (e.g., XGBoost, SVM) and also considers logistic regression for interpretable linear patterns.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]