Using social media for classifying actionable insights in disaster scenario

Ghosh, Samujjwal; Srijith, P. K.; Desarkar, Maunendra Sankar

doi:10.1007/s12572-017-0197-2

Cited by 13 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research created text classification models using tweet data based on SVM, J48 and NB classifiers. Although SVM with TF-IDF is still widely used for the development of text classification models [6][7][8][9], we found that the TMTA, using J48 with the BWF dataset, provided higher values for performance measurements than SVM with TF-IDF. In particular, the TMTA using J48 with the BWF dataset had a lower runtime than such widely used techniques as BoW and TF-IDF.…”

Section: Hypothesis Testingmentioning

confidence: 85%

See 1 more Smart Citation

Text classification model for methamphetamine-related tweets in Southeast Asia using dual data preprocessing techniques

Chayangkoon

Srivihok

2021

IJECE

View full text Add to dashboard Cite

<span>Methamphetamine addiction is a prominent problem in Southeast Asia. Drug addicts often discuss illegal activities on popular social networking services. These individuals spread messages on social media as a means of both buying and selling drugs online. This paper proposes a model, the “text classification model of methamphetamine tweets in Southeast Asia” (TMTA), to identify whether a tweet from Southeast Asia is related to methamphetamine abuse. The research addresses the weakness of bag of words (BoW) by introducing BoW and Word2Vec feature selection (BWF) techniques. A domain-based feature selection method was performed using the BoW dataset and Word2Vec. The BWF dataset provided a smaller number of features than the BoW and TF–IDF dataset. We experimented with three candidate classifiers: Support vector machine (SVM), decision tree (J48) and naive bayes (NB). We found that the J48 classifier with the BWF dataset provided the best performance for the TMTA in terms of accuracy (0.815), F-measure (0.818), Kappa (0.528), Matthews correlation coefficient (0.529) and high area under the ROC Curve (0.763). Moreover, TMTA provided the lowest runtime (3.480 seconds) using the J48 with the BWF dataset.</span>

show abstract

Section: Hypothesis Testingmentioning

confidence: 85%

“…Ghosh et al [8] addressed the multi-class classification problem for disaster events consisting of earthquakes, hurricanes, electrical outages and drought. The experimental tweets in the 2015 dataset related to the Nepal earthquake in April of that year.…”

Section: Introductionmentioning

confidence: 99%

Text classification model for methamphetamine-related tweets in Southeast Asia using dual data preprocessing techniques

Chayangkoon

Srivihok

2021

IJECE

View full text Add to dashboard Cite

show abstract

“…The results from the reviewed papers and articles show different SMA methods and tools. Most of the reviewed articles demonstrate the usage of sentiment analysis in different areas 54.54% of the articles reviewed uses sentiment analysis Su and Chen (2016), Vorvoreanu et al (2013), Chang et al (2017), Xiang et al (2016), Park et al (2016, He et al (2017), Stieglitz (2012, Anyanwu (2019), Shang et al (2018), Dong et al (2013,), Xu et al (2019), Dahal et al (2019), Kannan et al (2018), Martinez et al(2019), Alamsyah (2017), Barrelet et al (2016), Chen (2016), Chumwatana and Wongkolkitsilp (2019) Kannan et al (2018), Hu et al (2011), and Sachdeva and Mc Caffrey (2018, clustering technique 6.81% Jansen et al (2018), Myaeng et al (2016), and Ghosh et al (2017 , natural language processing 6.81% Barrelet et al (2016), Al Kubaizi et al (2015), and Saravan and Perepu ( 2019), text analysis 4.54% Dias et al (2018), andSingh et al (2018), event detection tool 2.27% Weiler (2013) and social network analysis 6.81% Alamsyah (2017), Udanor et al (2016), and Rahmani et al (2013).…”

Section: Sma Methods and Tools Usedmentioning

confidence: 99%

“…The study demonstrates how this technique can be used in wildfire events with good performance; however, the study didn't map the area with air pollution during wildfire events geographically. Ghosh et al (2017) introduces the study which used to classify tweets during disaster based on their insight they contain. The study performs clustering algorithm to create different clusters based on different classes.…”

Section: Summary Of Reviewed Articlesmentioning

confidence: 99%

“…The most usable platform for social media analytics was twitter. 77.27% of the reviewed articles use twitter as the social media platform and the study found that most of the analytics performed in twitter platform was sentiment analysis; Su and Chen (2016), Vorvoreanu et al (2013), Bukhari et al (2012), Xiang et al (2016), Park et al (2016), Stieglitz (2012), Myaeng (2016, Weiler (2013), Anyanwu (2019), Shang et al (2018), Dong et al (2019), Xu et al (2019), Dahal et al (2019), Singh et al (2018), Kannan et al (2018), Culotta (2010), Martinez et al (2019), Al Kubaizi et al (2015), Saravan and Perepu (2019), Alamsyah (2017), Barrelet et al (2016), Chen (2016), Chumwatana and Wongkolkitsilp (2019), Tian et al (2019), He et al (2019), Hu et al (2011), Sachdeva andMc Caffrey (2018), Udanor et al (2016), Wu et al (2018), Santander et al (2020, Ghosh et al (2017), Araya et al (2017, Rahmani et al (2013), andVon Hoffen et al (2019). 18.18% of the reviewed articles used Facebook; Vorvoreanu et al (2013), Bukhari et al (2012), Dias et al (2018), Jain et al (2015, Saravan and Perepu (2019), Chumwatana and Wongkolkitsilp (2019), Cvijikj andMi...…”

Section: Types Of Sm Platforms Used For Smamentioning

confidence: 99%

See 1 more Smart Citation

A Review of Usage and Applications of Social Media Analytics

Madila¹,

Dida²,

Kaijage³

2021

J INFORM SYSTEMS ENG

View full text Add to dashboard Cite

This paper presents the report of a social media analytics (SMA) review. The review conducted to find out the methods and tools used in social media analytics, types of social media platforms which the SMA are performed and the field which SMA has been performed. Social media contains a lot of user uploaded data in different formats like text, images, photos, video etc. These large volumes of data are converted in meaningful information which can be understood using different methods and tools which are called social media analytics. A literature review of articles published between 2010-2020 has been conducted using articles obtained from reputable databases IEEE Xplore, ACM digital, Emerald insight, Springer Link and Science direct. A number of 44 articles have been selected for review from 110 retrieved papers. The paper has been reviewed according to the study objectives. The study found that SMA tools and techniques which have been used are sentiment analysis, youtube analytics, visible intelligence, IBM Watson tool and predictive models. The social media platforms which were mostly used are twitter, facebook, youtube, trip advisor and blogs. SMA has been observed in different fields like agriculture, politics, health, social and business sector.

show abstract