Attention has long been considered the basis of traditional marketing models, serving as the foundation for consumer engagement with advertising. However, in today’s digital landscape, especially on social media, overwhelming advertising clutter makes it uncommon for advertisers and publishers to achieve high attention levels from consumers. This context makes conventional metrics like impressions and clicks inadequate, as they fail to capture meaningful engagement. Our research addresses this gap by exploring consumer interactions with advertisements under different low-attention types: focused, incidental, and divided. Leveraging neurophysiological measures based on cortical responses, eye-tracking, and electrodermal activity, we aim to provide new insights into attention dynamics and assess ads effectiveness on social medias, from both focal and peripheral perspectives. We conducted an experiment with 55 participants who scrolled through a simulated Instagram Web feed, following instructions to induce different attention levels. We recorded neurophysiological data and later assessed self-reported attention, recall, and recognition levels. The findings revealed that higher attention levels correlate with better brand recognition, with focused participants recalling brands more accurately than those in incidental or divided attention groups. Eye-tracking effectively distinguished attention levels, while EEG and EDA produced inconsistent results, indicating the need for further research on larger sample sizes into attention dynamics in digital contexts. Moreover, a combination of biometric and self-assessed data, better predicts brand recall than traditional survey-based methods, therefore opening to the possibility of considering new advertising frameworks based on attention metrics. Complementing the outdated Pay Per Click and Pay Per Impression frameworks, we propose Pay Per Attention and Pay Per Time Displayed models, set to become an industry started after being validated with further research. The implications of this study are significant, enhancing our understanding of how low attention influences brand recall while also suggesting that incorporating neurophysiological measures, especially eye-tracking data, into advertising strategies can lead to more effective budget allocation and improved prediction accuracy. For policymakers, it is underlined the importance of consumer privacy and transparency in biometric data use, advocating for new standards that protect consumer rights and foster fair competition in the advertising industry.
L'attenzione è considerata da tempo la base dei modelli di marketing tradizionali, costituendo il punto di partenza dell’interazione tra i consumatori e la pubblicità. Nonostante ciò, nell’odierno panorama digitale, e specialmente sulle piattaforme social, l’affollamento opprimente di pubblicità rende poco comune il raggiungimento di livelli di attenzione alti nei consumatori. Questo contesto rende a sua volta inadeguate le metriche convenzionali, come click e visualizzazioni, in quanto faticano a cogliere la sfaccettata natura dell’engagement. La nostra ricerca affronta questa carenza esplorando come i consumatori interagiscono con le pubblicità in diverse condizioni di bassa attenzione: focused, incidental e divided. Sfruttando metriche neurofisiologiche basate su risposte corticali, movimenti oculari e attività elettro dermica, miriamo a fornire maggiore consapevolezza sulle dinamiche dell’attenzione, contemporaneamente valutando l’efficacia delle inserzioni sui social network, considerando le prospettive focale e periferica. Abbiamo condotto un esperimento con 55 partecipanti, istruiti a scorrere un feed simulato di Instagram Web, seguendo istruzioni diverse in base al tipo di attenzione indotto. Abbiamo rilevato i dati biometrici dei partecipanti, e successivamente raccolto informazioni sui loro livelli di attenzione auto-dichiarata, recall e riconoscimento dei brand. I risultati rivelano che il livello di attenzione è correlato positivamente con il riconoscimento dei brand, avendo i partecipanti del gruppo focused dimostrato migliore memoria rispetto agli altri due. È possibile distinguere i tre tipi di attenzione in modo efficace con l’eye-tracker, mentre EEG e EDA hanno portato a risultati inconcludenti, mostrando la necessità di ulteriori studi sulle dinamiche di attenzione nei contesti digitali, utilizzando campioni più larghi. Inoltre, una combinazione di dati biometrici e auto-dichiarati prevede meglio il brand recall rispetto ai metodi tradizionali basati su sondaggi, aprendo quindi alla possibilità di considerare nuovi framework pubblicitari basati su metriche di attenzione. In aggiunta ai modelli obsoleti, quali Pay Per Click e Pay Per Impression, proponiamo i frameworks Pay Per Attention e Pay Per Time Displayed, destinati a diventare standard del settore una volta validati da ulteriori ricerche. Le implicazioni derivanti dal nostro studio sono significative. La nostra ricerca contribuisce a migliorare la comprensione di come la bassa attenzione influenzi il brand recall, suggerendo anche che l’inserimento nelle strategie di marketing di metriche neurofisiologiche, in particolare basate su eye-tracking, possa portare a una più efficiente allocazione del budget e migliorare l’accuratezza delle previsioni. Per i regolatori viene sottolineata l’importanza della privacy dei consumatori e della trasparenza nell’utilizzo dei dati biometrici, promuovendo nuovi standard che proteggano i diritti dei consumatori e la concorrenza leale nel settore pubblicitario.
Eyes don't lie: neuroscience-driven evaluation of advertising metrics
GABBIANI, LORENZO;BENEDINI, ALICE
2023/2024
Abstract
Attention has long been considered the basis of traditional marketing models, serving as the foundation for consumer engagement with advertising. However, in today’s digital landscape, especially on social media, overwhelming advertising clutter makes it uncommon for advertisers and publishers to achieve high attention levels from consumers. This context makes conventional metrics like impressions and clicks inadequate, as they fail to capture meaningful engagement. Our research addresses this gap by exploring consumer interactions with advertisements under different low-attention types: focused, incidental, and divided. Leveraging neurophysiological measures based on cortical responses, eye-tracking, and electrodermal activity, we aim to provide new insights into attention dynamics and assess ads effectiveness on social medias, from both focal and peripheral perspectives. We conducted an experiment with 55 participants who scrolled through a simulated Instagram Web feed, following instructions to induce different attention levels. We recorded neurophysiological data and later assessed self-reported attention, recall, and recognition levels. The findings revealed that higher attention levels correlate with better brand recognition, with focused participants recalling brands more accurately than those in incidental or divided attention groups. Eye-tracking effectively distinguished attention levels, while EEG and EDA produced inconsistent results, indicating the need for further research on larger sample sizes into attention dynamics in digital contexts. Moreover, a combination of biometric and self-assessed data, better predicts brand recall than traditional survey-based methods, therefore opening to the possibility of considering new advertising frameworks based on attention metrics. Complementing the outdated Pay Per Click and Pay Per Impression frameworks, we propose Pay Per Attention and Pay Per Time Displayed models, set to become an industry started after being validated with further research. The implications of this study are significant, enhancing our understanding of how low attention influences brand recall while also suggesting that incorporating neurophysiological measures, especially eye-tracking data, into advertising strategies can lead to more effective budget allocation and improved prediction accuracy. For policymakers, it is underlined the importance of consumer privacy and transparency in biometric data use, advocating for new standards that protect consumer rights and foster fair competition in the advertising industry.File | Dimensione | Formato | |
---|---|---|---|
2024_12_Benedini_Gabbiani_Tesi.pdf
solo utenti autorizzati a partire dal 11/11/2025
Descrizione: tesi
Dimensione
5.33 MB
Formato
Adobe PDF
|
5.33 MB | Adobe PDF | Visualizza/Apri |
2024_12_Benedini_Gabbiani_Executive Summary.pdf
solo utenti autorizzati a partire dal 11/11/2025
Descrizione: executive summary
Dimensione
1.45 MB
Formato
Adobe PDF
|
1.45 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/229919