Automatic Eyewitness Identification During Disasters by Forming a Feature-Word Dictionary

作     者：Shahzad Nazir Muhammad Asif Shahbaz Ahmad Hanan Aljuaid Shahbaz Ahmad Yazeed Ghadi Zubair nawaz 

作者机构：Department of Computer ScienceNational Textile UniversityFaisalabadPakistan Computer Sciences DepartmentCollege of Computer and Information SciencesPrincess Nourah bint Abdulrahman University(PNU)P.O.Box 84428Riyadh 11671Saudi Arabia Department of Software Engineering and Computer ScienceAl Ain UniversityAbu DhabiUnited Arab Emirates Department of Data ScienceUniversity of the PunjabPakistan 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第72卷第9期

页      面：4755-4769页

核心收录：

学科分类：0302[法学-政治学] 03[法学] 030204[法学-中共党史(含：党的学说与党的建设)] 

基　　金：This research is funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R54) Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia 

主　　题：Word dictionary social media eyewitness identification disasters 

摘      要：Social media provide digitally interactional technologies to facilitate information sharing and exchanging ***,in case of disasters,a massive corpus is placed on platforms such as *** accounts can benefit humanitarian organizations and agencies,but identifying the eyewitness Tweets related to the disaster from millions of Tweets is *** approaches have been developed to address this kind of *** recent state-of-the-art system was based on a manually created dictionary and this approach was further refined by introducing linguistic ***,these approaches suffer from limitations as they are dataset-dependent and not *** this paper,we proposed a method to identify eyewitnesses from *** experiment,we utilized 13 features discovered by the pioneer of this domain and can classify the tweets to determine the *** each feature,a dictionary of words was created with the Word Dictionary Maker algorithm,which is the crucial contribution of this *** algorithm inputs some terms relevant to a specific feature for its initialization and then creates the words ***,keyword matching for each feature in tweets is *** a feature exists in a tweet,it is termed as 1;otherwise,***,for 13 features,we created a file that reflects features in each *** classify the tweets based on features,Naïve Bayes,Random Forest,and Neural Network were *** approach was implemented on different disasters like earthquakes,floods,hurricanes,and Forest *** results were compared with the state-of-the-art linguistic rule-based system with 0.81 F-measure *** the same time,the proposed approach gained a 0.88 value of *** results were comparable as the proposed approach is not ***,it can be used for the identification of eyewitness accounts.