A comprehensive review of deep neuro-fuzzy system architectures and their optimization methods

Extracting the location of flooding events in urban systems and analyzing the semantic risk using social sensing data

The information propagation of emergencies in social networks is often accompanied by the dissemination of the topic and emotion. As a virtual sensor of public emergencies, social networks have been widely used in data mining, knowledge discovery, and machine learning. From the perspective of network, this study aims to explore the topic and emotion propagation mechanism, as well as the interaction and communication relations of the public in social networks under four types of emergencies, including public health events, accidents and disasters, social security events, and natural disasters. Event topics were identified by Word2vec and K-means clustering. The biLSTM model was used to identify emotion in posts. The propagation maps of topic and emotion were presented visually on the network, and the synergistic relationship between topic and emotion propagation as well as the communication characteristics of multiple subjects were analyzed. The results show that there were similarities and differences in the propagation mechanism of topic and emotion in different types of emergencies. There was a positive correlation between topic and emotion of different types of users in social networks in emergencies. Users with a high level of topic influence were often accompanied by a high level of emotion appeal.

https://www.mdpi.com/1424-8220/21/13/4516/pdf

Topic-Emotion Propagation Mechanism of Public Emergencies in Social Networks.

During the recent pandemic of COVID-19, an increasing amount of information has been propagated on social media. This situational information is valuable for public authorities. Therefore, this study characterized the propagation scale of situational information types by harnessing the power of natural language processing techniques and machine learning algorithms. We observed that the length of the post has a positive correlation with type 1 information (announcements), and negative words were mostly used in type 5 information (criticizing the government), whereas anxiety-related words have a negative effect on the amount of retweeted type 0 (precautions) and type 2 (donations) information. This type of research study not only contributes to the situational information literature by comprehensively defining categories but also provides data-oriented practical insights into information so that management authorities can formulate response strategies after the pandemic. Our approach is one of its kind and combines Twitter content features, user features and LIWC linguistic features with machine learning algorithms to analyze the propagation scale of situational information, and it achieved 77% accuracy with SVM while classifying the information categories.

Identifying and Characterizing the Propagation Scale of COVID-19 Situational Information on Twitter: A Hybrid Text Analytic Approach

Network analysis is a useful tool to analyse the interactions and structure of graphs that represent the relationships among entities, such as sectors within an urban system. Connecting entities in this way is vital in understanding the complexity of the modern world, and how to navigate these complexities during an event. However, the field of network analysis has grown rapidly since the 1970s to produce a vast array of available metrics that describe different graph properties. This diversity allows network analysis to be applied across myriad research domains and contexts, however widespread applications have produced polysemic metrics. Challenges arise in identifying which method of network analysis to adopt, which metrics to choose, and how many are suitable. This paper undertakes a structured review of literature to provide clarity on raison d'etre behind metric selection and suggests a way forward for applied network analysis. It is essential that future studies explicitly report the rationale behind metric choice and describe how the mathematics relates to target concepts and themes. An exploratory metric analysis is an important step in identifying the most important metrics and understanding redundant ones. Finally, where applicable, one should select an optimal number of metrics that describe the network both locally and globally, so as to understand the interactions and structure as holistically as possible.The online version contains supplementary material available at 10.1007/s41109-022-00476-w. 

/pdf/exploring-the-raison-detre-behind-metric-selection-in-2i1q721l.pdf

Exploring the raison d’etre behind metric selection in network analysis: a systematic review

Combining machine learning with social network analysis (SNA) can leverage vast amounts of social media data to better respond to crises. We present a case study using Twitter data from the March 2019 Nebraska floods in the United States, which caused over $1 billion in damage in the state and widespread evacuations of residents. We use a subset of machine learning, deep learning (DL), to classify text content of 11,982 tweets, and we integrate that with SNA to understand the structure of tweet interactions. Our DL approach pre‐trains our model with a DL language technique, BERT, and then trains the model using the standard training dataset to sort a dataset of tweets into classes tailored to crisis events. Several performance measures demonstrate that our two‐tiered trained model improves domain adaptation and generalization across different extreme weather event types. This approach identifies the role of Twitter during the damage containment stage of the flood. Our SNA identifies accounts that function as primary sources of information on Twitter. Together, these two approaches help crisis managers filter large volumes of data and overcome challenges faced by simple statistical models and other computational techniques to provide useful information during crises like flooding.

Stefan Morgan

Papers

Using deep learning and social network analysis to understand and manage extreme flooding