Search Results (40)

Natural disasters like wildfires pose significant threats to communities, which necessitates timely and effective disaster response strategies. While Aspect-based Sentiment Analysis (ABSA) has been widely used to extract sentiment-related information at the sub-sentence level, the corresponding field of Aspect-based Emotion Analysis (ABEA) remains underexplored due to dataset limitations and the increased complexity of emotion classification. In this study, we used EmoGRACE, a fine-tuned BERT-based model for ABEA, which we applied to georeferenced tweets of the 2020 California wildfires. The results for this case study reveal distinct spatio-temporal emotion patterns for wildfire-related aspect terms, with fear and sadness increasing near wildfire perimeters. This study demonstrates the feasibility of tracking emotion dynamics across disaster-affected regions and highlights the potential of ABEA in real-time disaster monitoring. The results suggest that ABEA can provide a nuanced understanding of public sentiment during crises for policymakers. Full article

The widespread use of mobile phones and social media platforms provides valuable information about users’ behavior and activities. Mobile phone data are rich on positional information, but lack semantic context. Conversely, geo-social media data reveal users’ opinions and activities, but are rather sparse in space and time. In the context of emergency management, both data types have been considered separately. To exploit their complementary nature and potential for emergency management, this paper introduces a novel methodology for improving situational awareness with the focus on urban events. For crowd detection, a spatial hot spot analysis of mobile phone data is used. The analysis of geo-social media data involves building spatio-temporal topic-sentiment clusters of posts. The results of the spatio-temporal contextual enrichment include unusual crowds associated with topics and sentiments derived from the analyzed geo-social media data. This methodology is demonstrated using the case study of the Vienna Pride. The results show how crowds change over time in terms of their location, size, topics discussed, and sentiments. Full article

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose a Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE), to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress-detection methodologies in terms of precision, recall, and interpretability. The results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on. Full article

The emergence of the COVID-19 pandemic, followed by policy measures to combat the virus, evoked public protest movements world-wide. These movements were formed not only in the virtual world but also through local protest gatherings. In contrast to previous research that studied movements in the virtual world through digital network analysis, this study recognizes the importance of the spatial dimension of social movements through local interaction. We therefore introduce a large-scale spatial–social network analysis of a georeferenced Twitter user network to understand the regional connections and transnational influences of the local movement through the virtual network. Our findings indicate that the virtual social network is distinctly structured along geographic and linguistic boundaries. Furthermore, our analysis of transnational influences reveals that the connections within Austria itself hold greater significance compared to their impact on external regions. Full article

With the vast amount of social media posts available online, topic modeling and sentiment analysis have become central methods to better understand and analyze online behavior and opinion. However, semantic and sentiment analysis have rarely been combined for joint topic-sentiment modeling which yields semantic topics associated with sentiments. Recent breakthroughs in natural language processing have also not been leveraged for joint topic-sentiment modeling so far. Inspired by these advancements, this paper presents a novel framework for joint topic-sentiment modeling of short texts based on pre-trained language models and a clustering approach. The method leverages techniques from dimensionality reduction and clustering for which multiple algorithms were considered. All configurations were experimentally compared against existing joint topic-sentiment models and an independent sequential baseline. Our framework produced clusters with semantic topic quality scores of up to $0.23$ while the best score among the previous approaches was $0.12$. The sentiment classification accuracy increased from $0.35$ to $0.72$ and the uniformity of sentiments within the clusters reached up to $0.9$ in contrast to the baseline of $0.56$. The presented approach can benefit various research areas such as disaster management where sentiments associated with topics can provide practical useful information. Full article

In the early stages of a disaster caused by a natural hazard (e.g., flood), the amount of available and useful information is low. To fill this informational gap, emergency responders are increasingly using data from geo-social media to gain insights from eyewitnesses to build a better understanding of the situation and design effective responses. However, filtering relevant content for this purpose poses a challenge. This work thus presents a comparison of different machine learning models (Naïve Bayes, Random Forest, Support Vector Machine, Convolutional Neural Networks, BERT) for semantic relevance classification of flood-related, German-language Tweets. For this, we relied on a four-category training data set created with the help of experts from human aid organisations. We identified fine-tuned BERT as the most suitable model, averaging a precision of 71% with most of the misclassifications occurring across similar classes. We thus demonstrate that our methodology helps in identifying relevant information for more efficient disaster management. Full article

Twitter, one of the most important social media platforms, has been in the headlines regularly since its acquisition by Elon Musk in October 2022. This acquisition has had a strong impact on the employees, functionality, and discourse on Twitter. So far, however, there has been no analysis that examines the perception of the acquisition by the users on the platform itself. For this purpose, in this paper, we use georeferenced Tweets from the US and classify them using a polarity-based sentiment analysis. We find that the number of Tweets about Twitter and Elon Musk has increased significantly, as have negative sentiments on the subject. Using a spatial hot spot analysis, we find distinct centres of discourse, but no clear evidence of their significant change over time. On the West Coast, however, we suspect the first signs of polarisation, which could be an important indication for the future development of discourse on Twitter. Full article

Cycling mobility contributes to better livability in cites, helps societies to reduce greenhouse gas emissions and their dependency on fossil fuels, and shows positive health effects. However, unattractive conditions, primarily inadequate infrastructure, hinder the further growth of cycling mobility. As interactions of cyclists with the (built) environment are complex, assessing potential impacts of an intervention aimed at improving physical conditions is not trivial. Despite a growing body of literature on various facets of cycling mobility, assessments are widely limited to a single method and thereby either focus on one detailed aspect or on one perspective. While multi-method and mixed methods studies are emerging, they are not embedded into a structured, integrated framework for assessing systemic effects of interventions yet. Therefore, we propose a conceptual integration of several relevant methods such as questionnaires, interviews, GIS analyses and human sensing. In this paper, we present a generic, extensible framework that offers guidance for developing and implementing case-specific mixed methods designs for multifaceted assessments of interventions. The framework supports domain experts and researchers across different stages of conducting a study. Results from this research further indicate the added value of mixed methods studies compared to single-method approaches. Full article

Field measurement campaigns with traffic participants using wearable sensors and questionnaires can be challenging to carry out because of inconsistent interfaces across manufacturers for accessing sensor data and campaign-specific questionnaire contents bear large potential for errors. We present an app able to consolidate data from multiple technical sensors and questionnaires. The functionality includes providing feedback for correct sensor platform mounting, accessing and storing all sensor and questionnaire data in a uniform data structure. To do this, the app implements a sensor data bus class that unifies data from technical sensors and questionnaires. The app can also be extended to accommodate other sensor platforms provided they have a suitable API. We also describe a database structure holding the data from multiple campaigns and test subjects in a privacy preserving fashion. Finally, we identify some potential issues and hints that practitioners may encounter when conducting a measurement campaign. Full article

Human-centered applications using wearable sensors in combination with machine learning have received a great deal of attention in the last couple of years. At the same time, wearable sensors have also evolved and are now able to accurately measure physiological signals and are, therefore, suitable for detecting body reactions to stress. The field of machine learning, or more precisely, deep learning, has been able to produce outstanding results. However, in order to produce these good results, large amounts of labeled data are needed, which, in the context of physiological data related to stress detection, are a great challenge to collect, as they usually require costly experiments or expert knowledge. This usually results in an imbalanced and small dataset, which makes it difficult to train a deep learning algorithm. In recent studies, this problem is tackled with data augmentation via a Generative Adversarial Network (GAN). Conditional GANs (cGAN) are particularly suitable for this as they provide the opportunity to feed auxiliary information such as a class label into the training process to generate labeled data. However, it has been found that during the training process of GANs, different problems usually occur, such as mode collapse or vanishing gradients. To tackle the problems mentioned above, we propose a Long Short-Term Memory (LSTM) network, combined with a Fully Convolutional Network (FCN) cGAN architecture, with an additional diversity term to generate synthetic physiological data, which are used to augment the training dataset to improve the performance of a binary classifier for stress detection. We evaluated the methodology on our collected physiological measurement dataset, and we were able to show that using the method, the performance of an LSTM and an FCN classifier could be improved. Further, we showed that the generated data could not be distinguished from the real data any longer. Full article

Trajectory data represent an essential source of information on travel behaviors and human mobility patterns, assuming a central role in a wide range of services related to transportation planning, personalized recommendation strategies, and resource management plans. The main issue when dealing with trajectory recordings, however, is characterized by temporary losses in the data collection, causing possible spatial–temporal gaps and missing trajectory segments. This is especially critical in those use cases based on non-repetitive individual motion traces, when the user’s missing information cannot be directly reconstructed due to the absence of historical individual repetitive routes. Inserted in the context of location-based trajectory modeling, we tackle the problem by proposing a technical parallelism with the natural language processing domain. Specifically, we introduce the use of the Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art language representation model, into the trajectory processing research field. By training deep bidirectional representations from unlabeled location sequences, jointly conditioned on both left and right context, we derive an explicit predicted estimation of the missing locations along the trace. The proposed framework, named TraceBERT, was tested on a real-world large-scale trajectory dataset of short-term tourists, exploring an effective attempt of adapting advanced language modeling approaches into mobility-based applications and demonstrating a prominent potential on trajectory reconstruction over traditional statistical approaches. Full article

The Longitudinal Employer-Household Dynamics Origin-Destination Employment Statistics (LODES) are an important city planning resource in the USA. However, curating these statistics is resource-intensive, and their accuracy deteriorates when changes in population and urban structures lead to shifts in commuter patterns. Our study area is the San Francisco Bay area, and it has seen rapid population growth over the past years, which makes frequent updates to LODES or the availability of an appropriate substitute desirable. In this paper, we derive mobility flows from a set of over 40 million georeferenced tweets of the study area and compare them with LODES data. These tweets are publicly available and offer fine spatial and temporal resolution. Based on an exploratory analysis of the Twitter data, we pose research questions addressing different aspects of the integration of LODES and Twitter data. Furthermore, we develop methods for their comparative analysis on different spatial scales: at the county, census tract, census block, and individual street segment level. We thereby show that Twitter data can be used to approximate LODES on the county level and on the street segment level, but it also contains information about non-commuting-related regular travel. Leveraging Twitter’s high temporal resolution, we also show how factors like rush hour times and weekends impact mobility. We discuss the merits and shortcomings of the different methods for use in urban planning and close with directions for future research avenues. Full article

The COVID-19 pandemic drastically highlighted the vulnerability of the elderly population towards viral and other infectious threats, illustrating that aging is accompanied by dysregulated immune responses currently summarized in terms like inflammaging and immunoparalysis. To gain a better understanding on the underlying mechanisms of the age-associated risk of adverse outcome in individuals experiencing a SARS-CoV-2 infection, we analyzed the impact of age on circulating monocyte phenotypes, activation markers and inflammatory cytokines including interleukin 6 (IL-6), IL-8 and tumor necrosis factor (TNF) in the context of COVID-19 disease progression and outcome in 110 patients. Our data indicate no age-associated differences in peripheral monocyte counts or subset composition. However, age and outcome are associated with differences in monocyte activation status. Moreover, a distinct cytokine pattern of IL-6, IL-8 and TNF in elderly survivors versus non-survivors, which consolidates over the time of hospitalization, suggests that older patients with adverse outcomes experience an inappropriate immune response, reminiscent of an inflammaging driven immunoparalysis. Our study underscores the value, necessity and importance of longitudinal monitoring in elderly COVID-19 patients, as dynamic changes after symptom onset can be observed, which allow for a differentiated insight into confounding factors that impact the complex pathogenesis following an infection with SARS-CoV-2. Full article

Social media platforms such as Twitter are considered a new mediator of collective action, in which various forms of civil movements unite around public posts, often using a common hashtag, thereby strengthening the movements. After 26 February 2018, the #AllforJan hashtag spread across the web when Ján Kuciak, a young journalist investigating corruption in Slovakia, and his fiancée were killed. The murder caused moral shock and mass protests in Slovakia and in several other European countries, as well. This paper investigates how this murder, and its follow-up events, were discussed on Twitter, in Europe, from 26 February to 15 March 2018. Our investigations, including spatiotemporal and sentiment analyses, combined with topic modeling, were conducted to comprehensively understand the trends and identify potential underlying factors in the escalation of the events. After a thorough data pre-processing including the extraction of spatial information from the users’ profile and the translation of non-English tweets, we clustered European countries based on the temporal patterns of tweeting activity in the analysis period and investigated how the sentiments of the tweets and the discussed topics varied over time in these clusters. Using this approach, we found that tweeting activity resonates not only with specific follow-up events, such as the funeral or the resignation of the Prime Minister, but in some cases, also with the political narrative of a given country affecting the course of discussions. Therefore, we argue that Twitter data serves as a unique and useful source of information for the analysis of such civil movements, as the analysis can reveal important patterns in terms of spatiotemporal and sentimental aspects, which may also help to understand protest escalation over space and time. Full article

Mobile map applications are increasingly used in various aspects of our lives, leading to an increase in different map use situations and, therefore, map use contexts. Several empirical usability studies have identified how map design is associated with and impacted by selected map use context attributes. This research seeks to expand on these studies and analyzes combinations of map use contexts to identify relevant contextual factors that influence mobile map design usability. In a study with 50 participants from Colombia, we assessed in an online survey the usability of 27 map design variations (consisting of three map-reading tasks, three base map styles, and three interactivity variants). We found that the overall map design is critical in supporting map-reading activities (e.g., identifying a location on a map was supported by a simplified base map, whereas selecting points on the map was supported by a more detailed base map). We then evaluated user patterns in the collected data with archetypal analysis. It was possible to create archetypal representations of the participants with a corresponding map design profile and establish a workflow for modeling patterns in usability and context data. We recommend that future research continues assessing archetypal analysis as it provides a means for context-based decision-making on map design adaptation and transferability. Full article