AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION
Twitter is one of most popular Internet-based social networking platform to share feelings, views, and opinions. In recent years, many researchers have utilized the social dynamic property of posted messages or tweets to predict civil unrest in advance. However, existing frameworks fail to describe...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
UUM Press
2019-12-01
|
| Series: | Journal of ICT |
| Subjects: | |
| Online Access: | https://e-journal.uum.edu.my/index.php/jict/article/view/12349 |
| _version_ | 1811314729150316544 |
|---|---|
| author | Md Kamrul Islam Md Manjur Ahmed Kamal Zuhairi Zamli Salman Mehbub |
| author_facet | Md Kamrul Islam Md Manjur Ahmed Kamal Zuhairi Zamli Salman Mehbub |
| author_sort | Md Kamrul Islam |
| collection | DOAJ |
| description |
Twitter is one of most popular Internet-based social networking platform to share feelings, views, and opinions. In recent years, many researchers have utilized the social dynamic property of posted messages or tweets to predict civil unrest in advance. However, existing frameworks fail to describe the low granularity level of tweets and how they work in offline mode. Moreover, most of them do not deal with cases where enough tweet information is not available. To overcome these limitations, this article proposes an online framework for analyzing tweet stream inpredicting future civil unrest events. The framework filters tweet stream and classifies tweets using linear Support Vector Machine (SVM) classifier. After that, the weight of the tweet is measured and distributed among extracted locations to update the overall weight in each location in a day in a fully online manner. The weight history is then used to predict the status of civil unrest in a location. The significant contributions of this article are (i) A new keyword dictionary with keyword score to quantify sentiment in extracting the low granularity level of knowledge (ii) A new diffusion model for extracting locations of interest and distributing the sentiment among the locations utilizing the concept of information diffusion and location graph to handle locations with insufficient information (iii) Estimating the probability of civil unrest and determining the stages of unrest in upcoming days. The performance of the proposed framework has been measured and compared with existing logistic regression based predictive framework. The results showed that the proposed framework outperformed the existing framework in terms of F1 score, accuracy, balanced accuracy, false acceptance rate, false rejection rate, and Matthews correlation coefficient.
|
| first_indexed | 2024-04-13T11:17:38Z |
| format | Article |
| id | doaj.art-6b92c92f96df4d6bb6edd56a9318b68a |
| institution | Directory Open Access Journal |
| issn | 1675-414X 2180-3862 |
| language | English |
| last_indexed | 2024-04-13T11:17:38Z |
| publishDate | 2019-12-01 |
| publisher | UUM Press |
| record_format | Article |
| series | Journal of ICT |
| spelling | doaj.art-6b92c92f96df4d6bb6edd56a9318b68a2022-12-22T02:48:55ZengUUM PressJournal of ICT1675-414X2180-38622019-12-01191AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSIONMd Kamrul Islam0Md Manjur Ahmed1Kamal Zuhairi Zamli2Salman Mehbub3Lorraine Research Laboratory in Computer Science and its Applications, University of Lorraine, FranceFaculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, MalaysiaFaculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, MalaysiaDepartment of Computer Science & Engineering, Jessore University of Science & Technology, Bangladesh Twitter is one of most popular Internet-based social networking platform to share feelings, views, and opinions. In recent years, many researchers have utilized the social dynamic property of posted messages or tweets to predict civil unrest in advance. However, existing frameworks fail to describe the low granularity level of tweets and how they work in offline mode. Moreover, most of them do not deal with cases where enough tweet information is not available. To overcome these limitations, this article proposes an online framework for analyzing tweet stream inpredicting future civil unrest events. The framework filters tweet stream and classifies tweets using linear Support Vector Machine (SVM) classifier. After that, the weight of the tweet is measured and distributed among extracted locations to update the overall weight in each location in a day in a fully online manner. The weight history is then used to predict the status of civil unrest in a location. The significant contributions of this article are (i) A new keyword dictionary with keyword score to quantify sentiment in extracting the low granularity level of knowledge (ii) A new diffusion model for extracting locations of interest and distributing the sentiment among the locations utilizing the concept of information diffusion and location graph to handle locations with insufficient information (iii) Estimating the probability of civil unrest and determining the stages of unrest in upcoming days. The performance of the proposed framework has been measured and compared with existing logistic regression based predictive framework. The results showed that the proposed framework outperformed the existing framework in terms of F1 score, accuracy, balanced accuracy, false acceptance rate, false rejection rate, and Matthews correlation coefficient. https://e-journal.uum.edu.my/index.php/jict/article/view/12349Text classificationinformation diffusionsentiment analysispolynomial regressionconnected graph |
| spellingShingle | Md Kamrul Islam Md Manjur Ahmed Kamal Zuhairi Zamli Salman Mehbub AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION Journal of ICT Text classification information diffusion sentiment analysis polynomial regression connected graph |
| title | AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION |
| title_full | AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION |
| title_fullStr | AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION |
| title_full_unstemmed | AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION |
| title_short | AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION |
| title_sort | online framework for civil unrest prediction using tweet stream based on tweet weight and event diffusion |
| topic | Text classification information diffusion sentiment analysis polynomial regression connected graph |
| url | https://e-journal.uum.edu.my/index.php/jict/article/view/12349 |
| work_keys_str_mv | AT mdkamrulislam anonlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion AT mdmanjurahmed anonlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion AT kamalzuhairizamli anonlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion AT salmanmehbub anonlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion AT mdkamrulislam onlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion AT mdmanjurahmed onlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion AT kamalzuhairizamli onlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion AT salmanmehbub onlineframeworkforcivilunrestpredictionusingtweetstreambasedontweetweightandeventdiffusion |