Detecting Dengue/Flu Infections Based on Tweets Using LSTM and Word Embedding

被引:18
作者
Amin, Samina [1 ]
Uddin, M. Irfan [1 ]
Zeb, M. Ali [1 ]
Alarood, Ala Abdulsalam [2 ]
Mahmoud, Marwan [3 ]
Alkinani, Monagi H. [4 ]
机构
[1] Kohat Univ Sci & Technol, Inst Comp, Kohat 2600, Pakistan
[2] Univ Jeddah, Coll Comp Sci & Engn, Jeddah 21959, Saudi Arabia
[3] King Abdulaziz Univ, Fac Appl Studies, Jeddah 21959, Saudi Arabia
[4] Univ Jeddah, Dept Comp Sci & Artificial Intelligence, Coll Comp Sci & Engn, Jeddah 21959, Saudi Arabia
关键词
Diseases; Epidemics; Monitoring; Social networking (online); Public healthcare; Social media; disease detection; deep learning; Word2Vec; LSTM; SOCIAL MEDIA; FEVER; TWITTER;
D O I
10.1109/ACCESS.2020.3031174
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the massive spike in the use of Online Social Network Sites (OSNSs) platforms such as Web 2.0, microblogs services and online blogs, etc., valuable information in the form of sentiment, thoughts, opinions, as well as epidemic outbreaks, etc. are transferred. With the OSNSs being widely accessible, this work aims at proposing a novel approach for disease (dengue or flu) detection based on social media posts. For this purpose, an automated approach is designed with the help of LSTM (Long Short Term Memory) and word embedding techniques. Then the performance of the proposed approach is validated using a set of standard evaluation matrices. In addition, the effectiveness of the selected models is evaluated with performance measurement techniques. The accuracy of the proposed research approach is evaluated using two word embedding techniques; Word2Vec with Skip-gram (SG) and Word2Vec with Continuous-bag-of-words (CBOW). Based on the results conducted in this paper the LSTM Word2Vec with CBOW achieved better results compared to LSTM with Word2Vec SG features embedding technique. Our findings prove that the proposed method yields 94% accuracy compared to state-of-the-art approaches. Consequently, LSTM performed better than other leading methods in the detection of disease-infected people in tweets. In the end, spatial analysis is performed to identify the disease infected region.
引用
收藏
页码:189054 / 189068
页数:15
相关论文
共 57 条
  • [1] Fake News Identification on Twitter with Hybrid CNN and RNN Models
    Ajao, Oluwaseun
    Bhowmik, Deepayan
    Zargari, Shahrzad
    [J]. SMSOCIETY'18: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON SOCIAL MEDIA AND SOCIETY, 2018, : 226 - 230
  • [2] Enhancement of Epidemiological Models for Dengue Fever Based on Twitter Data
    Albinati, Julio
    Meira Jr, Wagner
    Pappa, Gisele L.
    Teixeira, Mauro
    Marques-Toledo, Cecilia
    [J]. PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON DIGITAL HEALTH (DH'17), 2017, : 109 - 118
  • [3] Preliminary Flu Outbreak Prediction Using Twitter Posts Classification and Linear Regression With Historical Centers for Disease Control and Prevention Reports: Prediction Framework Study
    Alessa, Ali
    Faezipour, Miad
    [J]. JMIR PUBLIC HEALTH AND SURVEILLANCE, 2019, 5 (02): : 97 - 120
  • [4] A review of influenza detection and prediction through social networking sites
    Alessa, Ali
    Faezipour, Miad
    [J]. THEORETICAL BIOLOGY AND MEDICAL MODELLING, 2018, 15
  • [5] Ali H., 2017, J BIOEQUIV BIOAVAILA, V9, P473, DOI [10.4172/jbb.1000347, DOI 10.4172/jbb.1000347]
  • [6] Can We Predict a Riot? Disruptive Event Detection Using Twitter
    Alsaedi, Nasser
    Burnap, Pete
    Rana, Omer
    [J]. ACM TRANSACTIONS ON INTERNET TECHNOLOGY, 2017, 17 (02)
  • [7] [Anonymous], 2015, DEEP LEARNING NATURE, DOI [DOI 10.1038/NATURE14539, 10.1038/nature14539]
  • [8] [Anonymous], 2013, COMPUTER SCI
  • [9] [Anonymous], 2011, COMPUT LINGUIST
  • [10] Bark O., 2017, DEEP LEARNING APPROA