Flash Flood Information Retrieval System: Pseudocodes

These pseudocodes are a source for researchers and practitioners to understand and generate the relevance numerical features in the FF IR ML Dataset available a Linked Dataset published in (https://doi.org/10.17603/ds2-rwg3-v337). The Flash Flood Information Retrieval (FF-IR) system is a domain-specific search engine that accepts a past flash flood as an event of interest, fetches candidate webpages from the web, converts the webpages into numerical features, and uses the numerical features to make a prediction as to whether a candidate webpage contains relevant information about the event of interest or not. The system then returns a list of webpages that contain relevant information. The FF-IR outperforms direct Google searches by over 100%, measured by the F2-score. Natural hazard researchers and practitioners can use FF-IR to facilitate Flash Flood risk assessments and mitigation planning. The details of the system have been published and are added as Related Work (https://doi.org/10.1016/j.envsoft.2023.105734). These pseudocodes are used to generate the numerical features to represent a candidate webpage in the FF-IR system. Each of these features represent a similarity/relevance measure between the webpage and the FF event of interest. Further details regarding the pseudocodes are available in the readme file. The public access web software for the FF-IR system called Flood Finder 360 is currently under development and being continuosly updated ( https://www.floodfinder360.com/).