Text Classification of Flu-related Tweets Using FastText with Sentiment and Keyword Features

被引：14

作者：

Alessa, Ali ^{[1
]}

Faezipour, Miad ^{[1
,2
]}

Alhassan, Zakhriya ^{[3
]}

机构：

[1] Univ Bridgeport, Comp Sci & Engn Dept, Sch Engn, Bridgeport, CT 06601 USA

[2] Univ Bridgeport, Biomed Engn Dept, Sch Engn, Bridgeport, CT USA

[3] Univ Durham, Comp Sci Dept, Sch Engn & Comp Sci, Durham, England

来源：

2018 IEEE INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS (ICHI) | 2018年

关键词：

fastText; flu tweet classification; topic-related-keywords; sentiment; Social Networking Site;

D O I：

10.1109/ICHI.2018.00058

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this study, we present a framework for flu-prediction/detection based on the available data of Social Networking Sites (SNS). The framework uses a state-of-the-art text classifier, which is FastText, to classify Twitter posts into flu-related or flu-unrelated posts. The FastText based framework is trained and tested using a pre-labeled dataset and utilizing the features of sentiment analysis and predefined keyword occurrences in addition to textual features. Results show that the framework improves the accuracy, in addition to the efficiency of flu disease surveillance systems that use unstructured data such as posts of Social Networking Sites.

引用

页码：366 / 367

页数：2