INTERNATIONAL SEMINAR & THESIS PROJECT: Bio-signals in Information Systems and Marketing

  • Type: Practical Seminar / Master Thesis
  • Time:

    End of February 2023

A Cooperation between Politecnico di Milano and Karlsruhe Institute of Technology.

Starting in February 2023

Master Level Practical Seminars (4,5 ECTS) or Theses (30 ECTS)

INTRODUCTION

Bio-signals are nowadays being studied more intensely than ever to understand the processes within the human body and brain, which can inform technologies that help us understand and support physical and mental activities. Thanks to the technological developments of sensors integrated into devices that we use every day (e.g. Smartwatches, Headphones, etc.), it is possible to study this field more widely, trying to add quantitative data to the observation of human behavior.

Emotions and the implicit cognitive process can be detected from the analysis of bio-signals as individuals typically have low control over these processes, so, physiological changes in our body can give researchers a new way to study cognitive and affective processes. In Consumer Neuroscience, for example, we can use this world of data as insight into the human perception and evaluation of a specific product or situation, to predict future purchase behavior.  In Neuro-Information Systems (NeuroIS) research, we can apply cognitive neuroscience and neurophysiological theories to develop adaptive and self-regulation support systems, with the use of live biofeedback or develop IS interfaces that automatically adapt to a user's current state.

The goal of this international seminar is to investigate the physiological side of human behavior, using electrophysiological measurements (ECG – heart rate, EMG – muscle activity, EDA – sweat gland activity, or EEG – brain activity) under the supervision of experts from the domains of information systems, marketing, and bio-medics. We aim to both analyze how physiological responses impact behavior and how – from a managerial point – this research could help practitioners in designing products, services, or interfaces. The specific projects (that you can apply for) are listed below.


STRUCTURE

How does it work?

The projects will start in February 2023.

Students can apply for any one of the topics listed below and complete the project either as a practical seminar (4,5 ECTS) or as a Master Thesis (30 ECTS). The following practical seminar courses are selectable for KIT students:

  • T-WIWI-106207 Practical Seminar: Data-Driven Information Systems
  • T-WIWI-108765 Practical Seminar: Advanced Analytics
  • T-WIWI-109940 Spezialveranstaltung Wirtschaftsinformatik

You will work as a 2-person team or alone to carry out the project. By joining this project, you will get to network with students and researchers from both universities – either in person or virtually (remote attendance will be possible). 

The work for each project should include: (i) a literature review (ii) the design of an empirical study to test the research hypotheses, (iii) results in analysis and interpretation (iv) a discussion of academic, managerial, and policy-makers implications (v) limitation of the study and future research. The extent of these five parts will be adjusted to suit each project. 

To dive into bio-signals research easily, we will begin the project with a two-day Bootcamp introduction. You will learn about the key processes during such a study and we will provide you with Python code templates to make the start of bio-signal processing a piece of cake! Find out more about the dates, requirements, and application process below.


*The exact days are not fixed yet, but the calendar weeks (CW) are.

How can I apply?
You can apply if you have completed your Bachelor's degree, are fluent in English, and have previous experience with statistics and (ideally) with Python programming.
The application period is now open until February 6th, 2023. To submit your application, please write an e-mail to lorenzo puppo does-not-exist.kit edu including the following documents:

  • A letter of qualification (1p max.): This should indicate what qualifies you to conduct such a research project. We assume that you are motivated if you apply. So please focus on describing the skills and previous experiences that qualify you;
  • Your current transcript of records;
  • Your three most preferred topics (ranked – i.e. the first topic you name should be the one that you are interested in the most).
     

TOPICS

1.   Title: Pay attention to me: quantifying attention to advertising through consumer Neuroscience 
Supervisor (& Institution): Marco Mandolfo – PoliMi

Abstract: 

Attention has arguably become a currency in advertising research. Marketers spend billions on ads that run but do not reach their target because consumers simply do not pay attention to them. Current business models in the advertising industry are based on "pay-per-impression" and "pay-per-click" paradigms. Namely, publishers (i.e., organizations offering advertising space) at present ground their advertising fees on impression-based metrics; whereas advertisers (i.e., organizations that pay to have their advertising displayed) rely on click-based metrics. However, these metrics are hardly able to incorporate whether the viewer processed or recalled the advertising message. The present work envisions a shift towards a "pay-per-attention" paradigm. To reach such a goal, this work intends to: (i) conceptualize a set of metrics able to assess attention towards advertising using consumer neuroscience tools such as electroencephalography, electrodermal activity, and eye-tracking; (ii) assess possible relationships with current metrics adopted in the advertising industry (iii) test such attention metrics in a controlled laboratory environment. Overall, the work includes: (i) a thorough literature review of the behavioral mechanisms of consumer attention towards advertising, (ii) the design of a laboratory experiment to test research hypotheses, and (iii) an empirical investigation adopting a multimethod approach, which combines eye-tracking, self-reports, behavioral and physiological data. The work is expected to be structured as an empirical work with implications related to practitioners, policymakers, and academia.

Used Biosignal(s): Electroencephalography (EEG), electrodermal activity (EDA), and eye-tracking.

 
2.   Title: Advancing Open-Source EEG Headphones

Supervisor (& Institution): Michael Knierim – KIT

Abstract: 

How cool would it be if your headphones could actively improve your daily productivity and well-being? This reality might not be that far away! Wearable EEG systems are continuously being developed to monitor brain activity and support IT users' workload, flow, and fatigue. However, many of these functionality claims are rarely backed by scientific publications. To make these research practices more open and the technologies more available to people around the world, we have recently developed a headphone-based EEG system entirely out of 3D-printed and open-source components: https://github.com/MKnierim/openbci-headphones . In this project, you can improve this system by identifying a critical performance factor and developing and testing an innovative solution for it. Possible topics are: 

  • Programming a Java-based Widget to facilitate system setup 
  • Altering a 3D design to improve cable or cushion placement 
  • Identifying and investigating a promising new use case.

Used Biosignal(s): Electroencephalography (EEG), Electrocardiography (ECG).


3.    Title: The physiological side of consumer behavior: cognition, emotions, experience and how to measure them

Supervisor (& Institution): Debora Bettiga – PoliMi

Abstract:

Cognitive evaluations only partially explain consumer purchasing patterns, especially when consumers approach a product, a service, or an interface for the first time. In such an encounter, consumers may rely more on emotions and perceptions, as they cannot realistically evaluate product performances. Research in cognitive neurosciences (Dehaene, Changeux, & Naccache, 2011; Lane, Nadel, Allen, & Kaszniak, 2000; Smith & Lane, 2016), focusing on the distinction between implicit and explicit processes of cognition, confirms that the implicit-explicit distinction that applies to cognition generally also applies to emotions. Affective and unconscious drivers (Bagozzi et al. 2016) proved to have a strong influence on the customer's intention to perform a behavior, shaping the customer's decision-making processes (Bettiga and Lamberti 2017; 2018). This opens new space for investigation of these drivers for which boundaries, as well as effects on the purchase process, are still unclear (Ayadi, Paraschiv, & Vernette, 2017; De Keyser & Lariviere, 2014). Despite the acknowledged role of physiological, unconscious reactions in shaping consumers' evaluations and behaviors, research on this issue is still in its infancy. Research in consumer neuroscience, a new discipline based on the application of neuro- and bioscience in the managerial context, helps to individuate the unconscious and emotional reactions that a product or brand arises in consumers, to forecast their behaviors. Neuromarketing collects and integrates data about physiological individual responses, such as brain signals, skin conductance, breath, and heart rate or facial micro-expressions. The objective of this work is to investigate the physiological side of consumer behavior, by analyzing how physiological responses may impact the decision-making process. From a managerial point of view, the research should help practitioners in designing products, services, or interfaces that best suit their industry and properly target users. Students are expected to identify a specific topic of interest inside this stream. Overall, the thesis work should include: (i) a thorough literature review (ii) the design and development of empirical research to test the research hypotheses (multiple studies are suggested), (iii) results from analysis and interpretation (iv) discussion of academic, managerial and policy-makers implications (v) limitation of the study and future research.

Used Biosignal(s): Electroencephalography (EEG), Electrocardiography (ECG), Electrodermal activity (EDA), Facial micro-expression.

 
4.    Title: Developing an ECG Feature Processing API

Supervisor (& Institution): Ivo Benke – KIT

Abstract: 
When collecting ECG data what you get is raw output in form of physio-electronic signals. To derive meaningful insights from this information you need to calculate heart rate variability (HRV) features. Based on these HRV features you can, then, further process a data analysis pipeline, derive information regarding your health status, or train classifiers for the recognition of higher-level constructs such as stress, emotions, or flow. However, the calculation of these features is complex and requires time and knowledge. This project wants to reduce the effort for ECG researchers by automating the calculation of HRV features from raw ECG data. The goal is to develop a RESTful API where you can send a given input ECG dataset (from predefined sensors) and receive HRV features as output. The API shall be developed using common API design guidelines and based on the fast API framework in Python.

Used Biosignal(s): Electrocardiography (ECG).

 

5.  Title: Deciphering the Emotional Code of Employee-Customer Conversations using Biosignals

Supervisor (& Institution): Saskia Jacob - KIT

Abstract: 

Emotions play an essential role in employee-customer interaction. Neuromarketing is a new development in this literature field that has become more relevant in the last few years. Biosignals are the current methodical variable in this literature field to study as input data, that was not useable before (e.g., ECG, EDA, EMG, or EEG). Please conduct a short literature review on emotion detection methods using biosignals in neuromarketing and related disciplines. Based on this literature overview choose appropriate biosignals and detect patterns for different emotions in the data. Therefore, conduct a small experiment on the participant by inducing specific emotional states and measuring the corresponding biosignals.

Used Biosignal(s): Electroencephalography (EEG), Electrocardiography (ECG), Electrodermal activity (EDA), and Electromyography (EMG).

 

6.  Title: Ambulatory Emotion Monitoring 

Supervisor (& Institution): Tim Schneegans – KIT

Abstract: 

In this project, we tackle the challenge of measuring affective states in everyday life. Affective states play a major role in understanding human perception and behavior [1] and developing interventions [2]. To examine self-reports, movement, and physiological data, we will combine smartwatches [3] and potentially other sensors (e.g., EDA). The data can be used to build adaptive systems, such as an emotional map for the user. Along with the signal processing part, a major challenge is to ensure wearability and unobtrusiveness in everyday life. This involves a deep dive into Usability studies (e.g., Design Thinking).  Along with the credit points, the work will be rewarded with another step towards effective interventions that fit the user habits in real-life.

Used Biosignal(s): Electrocardiography (ECG), Electrodermal activity (EDA), photoplethysmogram (PPG). 


7.  Title: The role of cognitive load in purchase decisions: A machine learning study

Supervisor (& Institution): Tobias Weiß – Uni Gießen

Abstract: 

In this project, you work with electrocardiographic data which was recorded during a virtual reality experiment. Participants were asked to perform three multitasking challenges as shown in Figure 1 and a purchase decision as shown in Figure 2. First, participants traced a ball. It glowed red for the first five seconds and then became gray as the others. Second, participants traced the ball and performed calculations (plus/minus) simultaneously. Third, participants additionally counted the number of direction changes of a spinning object. In the purchase decision, participants were asked to evaluate either 3D printers or washing powders and select one of the products according to a set of given criteria. You use Python to design a machine learning workflow and apply shallow methods for classification. Your goal is to classify the different cognitive load levels and predict the self-reported difficulty level of the purchase decision. To this end, you compare different classifiers and feature engineering approaches.

Used Biosignal(s): Electrocardiography (ECG)

 
8.  Title: The physiology of well-being: improving knowledge workers' quality of life through Stress and Flow monitoring at the workplace

Supervisor (& Institution): Pierluigi Reali - PoliMi

Abstract:

Modern information and telecommunication technologies have been producing impressive changes in knowledge workers' lives. On one side, they greatly enhance productivity and foster the development of our society; on the other, they expose workers to chronic stress, which has proved a relevant risk factor for many psycho-physiological conditions, including cardiovascular diseases and depression. Conversely, feeling recurrent flow, namely the experience of being 'in the zone,' when you act with total involvement, losing track of time and self, has been suggested as being protective towards stress and burnout. Is it possible to classify different stress and flow levels through wearable devices measuring cardiovascular, respiratory, electrodermal, and electroencephalographic activity? That is what this project points to verify. Specifically, this work includes: i) performing a literature review of the most promising physiological features to evaluate stress and flow; ii) collecting the related physiological signals and self-assessed measures in a controlled laboratory environment (or equivalent out of the lab experience); iii) applying signal processing techniques to extract the features of interest; iv) applying statistical and machine learning strategies to perform feature selection, train and validate predictive models of stress and flow levels. Candidates are offered the opportunity to carry out an experimental study through all its phases, from experiment design and planning to analyzing and interpreting results. They will be advised by researchers having at least five years of experience in the field. Knowledge of MATLAB is required; experience with Python or R is warmly welcome but not necessary.

Used Biosignal(s): Electroencephalography (EEG), Electrocardiography (ECG), Electrodermal activity (EDA).

 

9.  Title: Headphones EEG in neuromarketing research.

Supervisor (& Institution): Lorenzo Del Puppo – KIT

Abstract:

Neuromarketing is an ever-evolving field and the last few decades have seen a growing interest. This discipline aims to use the methodologies and knowledge of cognitive neuroscience in the field of marketing and consumer psychology. Electroencephalography (EEG) is one of the most widely used methods as it is a minimally invasive and cost-effective neuroimaging method. Thanks to EEG we can capture brain activity with millisecond accuracy from cognitive processes. In the field of neuromarketing it is especially used by analyzing 'Hemispheric asymmetry': For example, frequency band asymmetries between the left and right frontal regions of the brain are linked to motivational approach and withdrawal behaviors concerning an item (e.g., a product) of attention. Wearable EEG systems are continuously being improved to try to detect and analyze brain activity outside lab conditions in more natural environments, improving ecological validity. 
With this project, students can investigate if we can obtain similar results about the analysis of some classical and established EEG patterns (Approach-Withdrawal index, emotion-related constructs, brainwave-based attention measurement) but using wearable EEG devices like "headphones EEG".  The student project includes (i) a choice of the experimental topic, (ii) a brief literature review, (iii) design of the experimental project using EEG headphones (iiii) Data collection and analysis.

Used Biosignal(s): Electroencephalography (EEG), Electrocardiography (ECG), Electrodermal activity (EDA).