Scientific Research
Nudging for the good – TAWNY in a scientific research setting. Application from a research perspective: What was only once a domain reserved for humans will in the future also be used by machines: Emotional Intelligence. Human data, be it physiological, video or text data, will be evaluated by machines in order to uncover patterns of behavior related to particular emotional states.
Already today, by using "affective computing", emotions can be identified, analyzed and classified using recognition algorithms. These states can then be projected onto machines so that products, services and experiences can be designed empathetically in the future. One scenario for integrating the human factor is seen in production systems. Here the detection of affective states based on vital signs can help to increase safety, health and efficiency within work flows and at the same time reduce failure rates within production processes. However, Emotion AI brings also major advance to Behavioral Economics as it continues to challenge the traditional view of consumers as rational decision-makers. Emotion recognition systems are today supporting behavioral researchers to uncover the systematic heuristics and biases that occur during human decision-making processes.
Together with the Chair of Marketing and Consumer Research at the Technical University of Munich, Rebeca Marichalar is conducting an experiment using the TAWNY Emotion Analytics Platform: the “Effect of nudging in online-shopping environments regarding the consumption of fast food.” What is nudging exactly? Rebeca explains: “It is a way of slightly modifying an environment where people make choices, introducing small interventions or incentives, which encourage people to make more beneficial decisions”. A well-known example would be digital speed control: when driving too fast in a play street, for example, a sad smiley is digitally displayed to the driver to incite him to reduce the speed.
Rebeca Marichala
Previous research focused on investigating the effect of nudges on healthy eating choices. Several types of nudges aiming to reduce the caloric intake during online shopping scenarios were tested, including for example the typical “traffic light” calorie system. Interestingly, a virtual assistant which provided feedback through facial expressions of approval or disapproval towards consumer choices was proved the most effective nudge. In a new line of research, Rebeca aims to understand the reasons for the effectiveness of this nudge and its relation with the emotional state. Nudges are nowadays commonly used by companies and governments to prompt consumer choices in online and offline settings. However, the reasons for the effectiveness of specific characteristics in nudges is still scarce. Rebeca’s thesis seeks to answer the question of what made the avatar more effective than the other nudge options.
TAWNY technology will therefore be put to test in an interesting experiment to find out whether emotions are involved in this subconscious process. By investigating the role of emotions on the efficacy of nudges to reduce caloric intake, Rebeca states: I want to find out whether the solution to my research question is related to human-machine empathy.
In the experiment, screened participants are to choose a full lunch meal from a fast-food delivery website without restrictions. Afterwards, within the paying and check-out process, an avatar provides feedback on the meal choice by expressing facial emotions depending on the caloric intake goal which will be calculated from the participants’ personal data. The avatar will display either a face of dissatisfaction when the participant chooses a meal over the calorie intake goal, or a facial expression of satisfaction when the calories stay within the recommended goal. During the whole experiment the participants facial expressions are recorded. Thanks to this, Rebeca will be able to process the recorded videos through the TAWNY EA Platform and analyze the relationship between the participants’ affective states and choice behavior.
Facial emotion detection via TAWNY EA’s technology
This research will contribute to bridge the gap between social researchers and AI practitioners who are now trying to break into the field of human emotions. By undertaking a cross-disciplined approach, showing how social scientists can leverage the power of new technologies as well as how technologists can deepen their knowledge through social sciences, TAWNY is connecting researchers to achieve its goal: understanding human emotions.
If you are interested in applying TAWNY into your scientific research setting, please feel free to reach out and contact us: info@tawny.ai