Search for: All records

Governments' use of social media during all phases of emergency management, especially during disasters, has increased dramatically in the past 20 years. Yet, implementation at the local government level in the United States remains haphazard. As technology and the role of social media evolve, there persists a need to understand the socio‐technical aspects of social media's employment in times of disaster. This study contributes to the growing social media literature by asking the following questions: what challenges remain and what lessons learned are being institutionalised at the local level of government? A qualitative analysis of 26 after action reports on Hurricane Irma (September 2017) by county, state, and federal governments and a four‐hour focus‐group session revealed dominant and subdominant themes, including: push/pull information; capacity and technical issues; inconsistent messaging; one‐way versus two‐way communication; timing of messages; and data collection. The paper concludes by discussing lessons learned, remaining challenges, evidence of organisational learning, and recommendations for future research.

 

This study evaluates the level of service of shared transportation facilities through mining geotagged data from social media and analyzing the perceptions of road users. An algorithm is developed adopting a text classification approach with contextual understanding to filter out relevant information related to users’ perceptions toward active mobility. Using a heuristic-based keyword matching approach produces about 75% tweets that are out of context, so that approach is deemed unsuitable for information extraction from Twitter. This study implements six different text classification models and compares the performance of these models for tweet classification. The model is applied to real-world data to filter out relevant information, and content analysis is performed to check the distribution of keywords within the filtered data. The text classification model “term frequency-inverse document frequency” vectorizer-based logistic regression model performed best at classifying the tweets. To select the best model, the performances of the models are compared based on precision, recall, F1 score (geometric mean of precision and recall), and accuracy metrics. The findings from the analysis show that the proposed method can help produce more relevant information on walking and biking facilities as well as safety concerns. By analyzing the sentiments of the filtered data, the existing condition of biking and walking facilities in the DC area can be inferred. This method can be a critical part of the decision support system to understand the qualitative level of service of existing transportation facilities.