Tourist Experiences Recommender System Based on Emotion Recognition with Wearable Data

Abstract

The collection of physiological data from people has been facilitated due to the mass use of cheap wearable devices. Although the accuracy is low compared to specialized healthcare devices, these can be widely applied in other contexts. This study proposes the architecture for a tourist experiences recommender system (TERS) based on the user’s emotional states who wear these devices. The issue lies in detecting emotion from Heart Rate (HR) measurements obtained from these wearables. Unlike most state-of-the-art studies, which have elicited emotions in controlled experiments and with high-accuracy sensors, this research’s challenge consisted of emotion recognition (ER) in the daily life context of users based on the gathering of HR data. Furthermore, an objective was to generate the tourist recommendation considering the emotional state of the device wearer. The method used comprises three main phases: The first was the collection of HR measurements and labeling emotions through mobile applications. The second was emotional detection using deep learning algorithms. The final phase was the design and validation of the TERS-ER. In this way, a dataset of HR measurements labeled with emotions was obtained as results. Among the different algorithms tested for ER, the hybrid model of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks had promising results. Moreover, concerning TERS, Collaborative Filtering (CF) using CNN showed better performance.

Research on dance teaching methods based on emotion recognition and emotion analysis

“…The effective SSL was learning from unlabeled data and improving data efficiency, it contrasted SSL with supervised learning while training convolutional neural networks (CNN) for emotion identification. The increasing accessibility of physiological data via wearable technologies, a recommender system for tourist experiences (TERS) [16] based on user's emotional states were suggested. It tackled problems with recognizing emotions from heart rate data in day to day living.…”

Visualization for Emotion Detection in Mobile-Based Land Monitoring Using User-Centred Design

“…Prototype Evolve Discover Santamaria-Granados, L., Mendoza-Moreno et.al [6] to first identify the elements of the emotion-based tourist recommender frameworks, a literature review was conducted. In order to recognize the user's emotional state as a pertinent contextual aspect in the fulfilment of the suggestion, wearable devices' physical data must be integrated, but this study exposed a gap in that process.…”

“…The data balance component sizes the dataset for the aforementioned and modifies the label names according to emotional states or quadrants. To assess the effectiveness of affective detection methods in Figure 4, it also employs class balance techniques [6].…”

Emotion Recognition with Pre-Trained Transformers Using Multimodal Signals

“…An example of a deep-learning approach is provided by the work of Santamaria et al [18], where they employ models based on Convolutional Neural Networks (CNN) to perform emotion recognition. Another example is the work of Harper and Southern [19], who use a combination of Recurrent Neural Networks (RNN) and CNNs.…”