By the same authors

Deep Learning and Word Embeddings for Tweet Classification for Crisis Response

Research output: Contribution to conferencePaper

Author(s)

Department/unit(s)

Conference

ConferenceThe 3rd National Computing Colleges Conference
Abbreviated titleNC3
CountrySaudi Arabia
CityAbha
Conference date(s)8/10/189/10/18
Internet address

Publication details

DatePublished - 8 Oct 2018
Number of pages5
Original languageEnglish

Abstract

Tradition tweet classification models for crisis response focus on convolutional layers and domain-specific word embeddings. In this paper, we study the application of different neural networks with general-purpose and domain-specific word embeddings to investigate their ability to improve the performance of tweet classification models. We evaluate four tweet classification models on CrisisNLP dataset and obtain comparable results which indicates that general-purpose word embedding such as GloVe can be used instead of domain-specific word embedding especially with Bi-LSTM where results reported the highest performance of 62.04% F1 score.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations