Wildfires and social media discourse: exploring mental health and emotional wellbeing through Twitter.

Introduction: The rise in global temperatures due to climate change has escalated the frequency and intensity of wildfires worldwide. Beyond their direct impact on physical health, these wildfires can significantly impact mental health. Conventional mental health studies predominantly rely on surveys, often constrained by limited sample sizes, high costs, and time constraints. As a result, there is an increasing interest in accessing social media data to study the effects of wildfires on mental health. Methods: In this study, we focused on Twitter users affected by the California Tubbs Fire in 2017 to extract data signals related to emotional well-being and mental health. Our analysis aimed to investigate tweets posted during the Tubbs Fire disaster to gain deeper insights into their impact on individuals. Data were collected from October 8 to October 31, 2017, encompassing the peak activity period. Various analytical methods were employed to explore word usage, sentiment, temporal patterns of word occurrence, and emerging topics associated with the unfolding crisis. Results: The findings show increased user engagement on wildfire-related Tweets, particularly during nighttime and early morning, especially at the onset of wildfire incidents. Subsequent exploration of emotional categories using Linguistic Inquiry and Word Count (LIWC) revealed a substantial presence of negative emotions at 43.0%, juxtaposed with simultaneous positivity in 23.1% of tweets. This dual emotional expression suggests a nuanced and complex landscape, unveiling concerns and community support within conversations. Stress concerns were notably expressed in 36.3% of the tweets. The main discussion topics were air quality, emotional exhaustion, and criticism of the president's response to the wildfire emergency. Discussion: Social media data, particularly the data collected from Twitter during wildfires, provides an opportunity to evaluate the psychological impact on affected communities immediately. This data can be used by public health authorities to launch targeted media campaigns in areas and hours where users are more active. Such campaigns can raise awareness about mental health during disasters and connect individuals with relevant resources. The effectiveness of these campaigns can be enhanced by tailoring outreach efforts based on prevalent issues highlighted by users. This ensures that individuals receive prompt support and mitigates the psychological impacts of wildfire disasters.

Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study.

BACKGROUND: Early identification of mental disorder symptoms is crucial for timely treatment and reduction of recurring symptoms and disabilities. A tool to help individuals recognize warning signs is important. We posit that such a tool would have to rely on longitudinal analysis of patterns and trends in the individual's daily activities and mood, which can now be captured through data from wearable activity trackers, speech recordings from mobile devices, and the individual's own description of their mental state. In this paper, we describe such a tool developed by our team to detect early signs of depression, anxiety, and stress. OBJECTIVE: This study aims to examine three questions about the effectiveness of machine learning models constructed based on multimodal data from wearables, speech, and self-reports: (1) How does speech about issues of personal context differ from speech while reading a neutral text, what type of speech data are more helpful in detecting mental health indicators, and how is the quality of the machine learning models influenced by multilanguage data? (2) Does accuracy improve with longitudinal data collection and how, and what are the most important features? and (3) How do personalized machine learning models compare against population-level models? METHODS: We collect longitudinal data to aid machine learning in accurately identifying patterns of mental disorder symptoms. We developed an app that collects voice, physiological, and activity data. Physiological and activity data are provided by a variety of off-the-shelf fitness trackers, that record steps, active minutes, duration of sleeping stages (rapid eye movement, deep, and light sleep), calories consumed, distance walked, heart rate, and speed. We also collect voice recordings of users reading specific texts and answering open-ended questions chosen randomly from a set of questions without repetition. Finally, the app collects users' answers to the Depression, Anxiety, and Stress Scale. The collected data from wearable devices and voice recordings will be used to train machine learning models to predict the levels of anxiety, stress, and depression in participants. RESULTS: The study is ongoing, and data collection will be completed by November 2023. We expect to recruit at least 50 participants attending 2 major universities (in Canada and Mexico) fluent in English or Spanish. The study will include participants aged between 18 and 35 years, with no communication disorders, acute neurological diseases, or history of brain damage. Data collection complied with ethical and privacy requirements. CONCLUSIONS: The study aims to advance personalized machine learning for mental health; generate a data set to predict Depression, Anxiety, and Stress Scale results; and deploy a framework for early detection of depression, anxiety, and stress. Our long-term goal is to develop a noninvasive and objective method for collecting mental health data and promptly detecting mental disorder symptoms. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/48210.

Measuring the Effectiveness of a Multicomponent Program to Manage Academic Stress through a Resilience to Stress Index.

In this work, we evaluate the effectiveness of a multicomponent program that includes psychoeducation in academic stress, mindfulness training, and biofeedback-assisted mindfulness, while enhancing the Resilience to Stress Index (RSI) of students through the control of autonomic recovery from psychological stress. Participants are university students enrolled in a program of excellence and are granted an academic scholarship. The dataset consists of an intentional sample of 38 undergraduate students with high academic performance, 71% (27) women, 29% (11) men, and 0% (0) non-binary, with an average age of 20 years. The group belongs to the "Leaders of Tomorrow" scholarship program from Tecnológico de Monterrey University, in Mexico. The program is structured in 16 individual sessions during an eight-week period, divided into three phases: pre-test evaluation, training program, and post-test evaluation. During the evaluation test, an assessment of the psychophysiological stress profile is performed while the participants undergo a stress test; it includes simultaneous recording of skin conductance, breathing rate, blood volume pulse, heart rate, and heart rate variability. Based on the pre-test and post-test psychophysiological variables, an RSI is computed under the assumption that changes in physiological signals due to stress can be compared against a calibration stage. The results show that approximately 66% of the participants improved their academic stress management after the multicomponent intervention program. A Welch's t-test showed a difference in mean RSI scores (t = -2.30, p = 0.025) between the pre-test and post-test phases. Our findings show that the multicomponent program promoted positive changes in the RSI and in the management of the psychophysiological responses to academic stress.

Towards a Resilience to Stress Index Based on Physiological Response: A Machine Learning Approach.

This study proposes a new index to measure the resilience of an individual to stress, based on the changes of specific physiological variables. These variables include electromyography, which is the muscle response, blood volume pulse, breathing rate, peripheral temperature, and skin conductance. We measured the data with a biofeedback device from 71 individuals subjected to a 10-min psychophysiological stress test. The data exploration revealed that features' variability among test phases could be observed in a two-dimensional space with Principal Components Analysis (PCA). In this work, we demonstrate that the values of each feature within a phase are well organized in clusters. The new index we propose, Resilience to Stress Index (RSI), is based on this observation. To compute the index, we used non-supervised machine learning methods to calculate the inter-cluster distances, specifically using the following four methods: Euclidean Distance of PCA, Mahalanobis Distance, Cluster Validity Index Distance, and Euclidean Distance of Kernel PCA. While there was no statistically significant difference (p>0.01) among the methods, we recommend using Mahalanobis, since this method provides higher monotonic association with the Resilience in Mexicans (RESI-M) scale. Results are encouraging since we demonstrated that the computation of a reliable RSI is possible. To validate the new index, we undertook two tasks: a comparison of the RSI against the RESI-M, and a Spearman correlation between phases one and five to determine if the behavior is resilient or not. The computation of the RSI of an individual has a broader scope in mind, and it is to understand and to support mental health. The benefits of having a metric that measures resilience to stress are multiple; for instance, to the extent that individuals can track their resilience to stress, they can improve their everyday life.

Choosing the Best Sensor Fusion Method: A Machine-Learning Approach.

Multi-sensor fusion refers to methods used for combining information coming from several sensors (in some cases, different ones) with the aim to make one sensor compensate for the weaknesses of others or to improve the overall accuracy or the reliability of a decision-making process. Indeed, this area has made progress, and the combined use of several sensors has been so successful that many authors proposed variants of fusion methods, to the point that it is now hard to tell which of them is the best for a given set of sensors and a given application context. To address the issue of choosing an adequate fusion method, we recently proposed a machine-learning data-driven approach able to predict the best merging strategy. This approach uses a meta-data set with the Statistical signatures extracted from data sets of a particular domain, from which we train a prediction model. However, the mentioned work is restricted to the recognition of human activities. In this paper, we propose to extend our previous work to other very different contexts, such as gas detection and grammatical face expression identification, in order to test its generality. The extensions of the method are presented in this paper. Our experimental results show that our extended model predicts the best fusion method well for a given data set, making us able to claim a broad generality for our sensor fusion method.

Multi-Sensor Fusion for Activity Recognition-A Survey.

In Ambient Intelligence (AmI), the activity a user is engaged in is an essential part of the context, so its recognition is of paramount importance for applications in areas like sports, medicine, personal safety, and so forth. The concurrent use of multiple sensors for recognition of human activities in AmI is a good practice because the information missed by one sensor can sometimes be provided by the others and many works have shown an accuracy improvement compared to single sensors. However, there are many different ways of integrating the information of each sensor and almost every author reporting sensor fusion for activity recognition uses a different variant or combination of fusion methods, so the need for clear guidelines and generalizations in sensor data integration seems evident. In this survey we review, following a classification, the many fusion methods for information acquired from sensors that have been proposed in the literature for activity recognition; we examine their relative merits, either as they are reported and sometimes even replicated and a comparison of these methods is made, as well as an assessment of the trends in the area.

Virtual Sensors for Optimal Integration of Human Activity Data.

Sensors are becoming more and more ubiquitous as their price and availability continue to improve, and as they are the source of information for many important tasks. However, the use of sensors has to deal with noise and failures. The lack of reliability in the sensors has led to many forms of redundancy, but simple solutions are not always the best, and the precise way in which several sensors are combined has a big impact on the overall result. In this paper, we discuss how to deal with the combination of information coming from different sensors, acting thus as "virtual sensors", in the context of human activity recognition, in a systematic way, aiming for optimality. To achieve this goal, we construct meta-datasets containing the "signatures" of individual datasets, and apply machine-learning methods in order to distinguish when each possible combination method could be actually the best. We present specific results based on experimentation, supporting our claims of optimality.

Towards an Efficient One-Class Classifier for Mobile Devices and Wearable Sensors on the Context of Personal Risk Detection.

In this work, we present a first step towards an efficient one-class classifier well suited for mobile devices to be implemented as part of a user application coupled with wearable sensors in the context of personal risk detection. We compared one-class Support Vector Machine (ocSVM) and OCKRA (One-Class K-means with Randomly-projected features Algorithm). Both classifiers were tested using four versions of the publicly available PRIDE (Personal RIsk DEtection) dataset. The first version is the original PRIDE dataset, which is based only on time-domain features. We created a second version that is simply an extension of the original dataset with new attributes in the frequency domain. The other two datasets are a subset of these two versions, after a feature selection procedure based on a correlation matrix analysis followed by a Principal Component Analysis. All experiments were focused on the performance of the classifiers as well as on the execution time during the training and classification processes. Therefore, our goal in this work is twofold: we aim at reducing execution time but at the same time maintaining a good classification performance. Our results show that OCKRA achieved on average, 89.1% of Area Under the Curve (AUC) using the full set of features and 83.7% when trained using a subset of them. Furthermore, regarding execution time, OCKRA reports in the best case a 33.1% gain when using a subset of the feature vector, instead of the full set of features. These results are better than those reported by ocSVM, in which case, even though the AUCs are very close to each other, execution times are significantly higher in all cases, for example, more than 20 h versus less than an hour in the worst-case scenario. Having in mind the trade-off between classification performance and efficiency, our results support the choice of OCKRA as our best candidate so far for a mobile implementation where less processing and memory resources are at hand. OCKRA reports a very encouraging speed-up without sacrificing the classifier performance when using the PRIDE dataset based only on time-domain attributes after a feature selection procedure.

Ensemble of One-Class Classifiers for Personal Risk Detection Based on Wearable Sensor Data.

This study introduces the One-Class K-means with Randomly-projected features Algorithm (OCKRA). OCKRA is an ensemble of one-class classifiers built over multiple projections of a dataset according to random feature subsets. Algorithms found in the literature spread over a wide range of applications where ensembles of one-class classifiers have been satisfactorily applied; however, none is oriented to the area under our study: personal risk detection. OCKRA has been designed with the aim of improving the detection performance in the problem posed by the Personal RIsk DEtection(PRIDE) dataset. PRIDE was built based on 23 test subjects, where the data for each user were captured using a set of sensors embedded in a wearable band. The performance of OCKRA was compared against support vector machine and three versions of the Parzen window classifier. On average, experimental results show that OCKRA outperformed the other classifiers for at least 0.53% of the area under the curve (AUC). In addition, OCKRA achieved an AUC above 90% for more than 57% of the users.

Mining IP to Domain Name Interactions to Detect DNS Flood Attacks on Recursive DNS Servers.

The Domain Name System (DNS) is a critical infrastructure of any network, and, not surprisingly a common target of cybercrime. There are numerous works that analyse higher level DNS traffic to detect anomalies in the DNS or any other network service. By contrast, few efforts have been made to study and protect the recursive DNS level. In this paper, we introduce a novel abstraction of the recursive DNS traffic to detect a flooding attack, a kind of Distributed Denial of Service (DDoS). The crux of our abstraction lies on a simple observation: Recursive DNS queries, from IP addresses to domain names, form social groups; hence, a DDoS attack should result in drastic changes on DNS social structure. We have built an anomaly-based detection mechanism, which, given a time window of DNS usage, makes use of features that attempt to capture the DNS social structure, including a heuristic that estimates group composition. Our detection mechanism has been successfully validated (in a simulated and controlled setting) and with it the suitability of our abstraction to detect flooding attacks. To the best of our knowledge, this is the first time that work is successful in using this abstraction to detect these kinds of attacks at the recursive level. Before concluding the paper, we motivate further research directions considering this new abstraction, so we have designed and tested two additional experiments which exhibit promising results to detect other types of anomalies in recursive DNS servers.