Child abuse and domestic abuse: Content and feature analysis from social media disclosures

Sudha Subramani; Hua Wang; Md Rafiqul Islam; Anwaar Ul-Haq; Manjula O'Connor

doi:10.1007/978-3-319-92013-9_14

Child abuse and domestic abuse: Content and feature analysis from social media disclosures

Sudha Subramani, Hua Wang, Md Rafiqul Islam, Anwaar Ul-Haq, Manjula O'Connor

Research output: Book chapter/Published conference paper › Conference paper › peer-review

12 Citations (Scopus)

Abstract

Due to increase in popularity of social media, people have started discussing their thoughts and opinions in the form of textual posts. Currently, the people tend to disclose even the socially tabooed topics such as Child Abuse (CA), and Domestic Abuse (DA) to receive the desired response and social support in turn. The increasing volume of abuse related posts being shared on social media is of great interest for public health sectors and family welfare organizations to monitor the public health and promote support services. However, due to the large volume, high velocity and huge variety of context and content of user generated data, it is diﬃcult to mine the diﬀerent kinds of abuse (CA and DA) related posts from other general posts, that ﬂood over the web. Hence, this paper aims to discover and diﬀerentiate the characteristics of CA and DA posts from the massive user generated posts, with the underlying context. Various features such as psycholinguistic, textual and sentimental features are analyzed and Machine Learning techniques are trained to analyze the predictive power of extracted features. Hence, the resulting model achieves more predictive power with high accuracy in classifying possible cases of abuse related posts from diverse user posts.

Original language	English
Title of host publication	Databases theory and applications
Subtitle of host publication	29th Australasian Database Conference, ADC 2018, Gold Coast, QLD, Australia, May 24-27, 2018, proceedings
Editors	Junhu Wang, Cong Gao, Jinjun Chen, Jianzhong Qi
Place of Publication	Champagne, Switzerland
Publisher	Springer
Chapter	14
Pages	174-185
Number of pages	12
Volume	10837
ISBN (Electronic)	9783319920139
ISBN (Print)	9783319920122
DOIs	https://doi.org/10.1007/978-3-319-92013-9_14
Publication status	Published - 2018
Event	29th Australasian Database Conference - Griffith University, Gold Coast, Australia Duration: 24 May 2018 → 27 May 2018 http://www.ict.griffith.edu.au/conferences/adc2018/

Conference

Conference	29th Australasian Database Conference
Country/Territory	Australia
City	Gold Coast
Period	24/05/18 → 27/05/18
Other	The Australasian Database Conference series is an annual forum for sharing the latest research progresses and novel applications of database systems, data driven applications and data analytics for researchers and practitioners in these areas from Australia, New Zealand and in the world. The 29th edition of the Australasian Database Conference, ADC 2018, will be co-located with 23rd International Conference on Database Systems For Advanced Applications (DASFAA 2018) in Gold Coast, Australia. ADC 2018 will be a key event of the 4-day Australasian Database Research Week. In addition to regular research papers, industry papers, demo sessions, and plenary poster sessions, ADC 2018 will also feature multiple keynote speeches and tutorials given by world-leading researchers and industry leaders.
Internet address	http://www.ict.griffith.edu.au/conferences/adc2018/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-319-92013-9_14

Cite this

Subramani, S., Wang, H., Islam, M. R., Ul-Haq, A., & O'Connor, M. (2018). Child abuse and domestic abuse: Content and feature analysis from social media disclosures. In J. Wang, C. Gao, J. Chen, & J. Qi (Eds.), Databases theory and applications: 29th Australasian Database Conference, ADC 2018, Gold Coast, QLD, Australia, May 24-27, 2018, proceedings (Vol. 10837, pp. 174-185). Springer. https://doi.org/10.1007/978-3-319-92013-9_14

Subramani, Sudha ; Wang, Hua ; Islam, Md Rafiqul et al. / Child abuse and domestic abuse : Content and feature analysis from social media disclosures. Databases theory and applications: 29th Australasian Database Conference, ADC 2018, Gold Coast, QLD, Australia, May 24-27, 2018, proceedings. editor / Junhu Wang ; Cong Gao ; Jinjun Chen ; Jianzhong Qi. Vol. 10837 Champagne, Switzerland : Springer, 2018. pp. 174-185

@inproceedings{5e3904c7cb3f4f87b1dd63b93c7f2b2a,

title = "Child abuse and domestic abuse: Content and feature analysis from social media disclosures",

abstract = "Due to increase in popularity of social media, people have started discussing their thoughts and opinions in the form of textual posts. Currently, the people tend to disclose even the socially tabooed topics such as Child Abuse (CA), and Domestic Abuse (DA) to receive the desired response and social support in turn. The increasing volume of abuse related posts being shared on social media is of great interest for public health sectors and family welfare organizations to monitor the public health and promote support services. However, due to the large volume, high velocity and huge variety of context and content of user generated data, it is diﬃcult to mine the diﬀerent kinds of abuse (CA and DA) related posts from other general posts, that ﬂood over the web. Hence, this paper aims to discover and diﬀerentiate the characteristics of CA and DA posts from the massive user generated posts, with the underlying context. Various features such as psycholinguistic, textual and sentimental features are analyzed and Machine Learning techniques are trained to analyze the predictive power of extracted features. Hence, the resulting model achieves more predictive power with high accuracy in classifying possible cases of abuse related posts from diverse user posts.",

keywords = "Child Abuse, Domestic Abuse, Social media, Text mining, Machine learning",

author = "Sudha Subramani and Hua Wang and Islam, {Md Rafiqul} and Anwaar Ul-Haq and Manjula O'Connor",

year = "2018",

doi = "10.1007/978-3-319-92013-9_14",

language = "English",

isbn = "9783319920122",

volume = "10837",

pages = "174--185",

editor = "Junhu Wang and Cong Gao and Jinjun Chen and Jianzhong Qi",

booktitle = "Databases theory and applications",

publisher = "Springer",

address = "United States",

note = "29th Australasian Database Conference ; Conference date: 24-05-2018 Through 27-05-2018",

url = "http://www.ict.griffith.edu.au/conferences/adc2018/",

}

Subramani, S, Wang, H, Islam, MR , Ul-Haq, A & O'Connor, M 2018, Child abuse and domestic abuse: Content and feature analysis from social media disclosures. in J Wang, C Gao, J Chen & J Qi (eds), Databases theory and applications: 29th Australasian Database Conference, ADC 2018, Gold Coast, QLD, Australia, May 24-27, 2018, proceedings. vol. 10837, Springer, Champagne, Switzerland, pp. 174-185, 29th Australasian Database Conference, Gold Coast, Queensland, Australia, 24/05/18. https://doi.org/10.1007/978-3-319-92013-9_14

Child abuse and domestic abuse: Content and feature analysis from social media disclosures. / Subramani, Sudha; Wang, Hua; Islam, Md Rafiqul et al.
Databases theory and applications: 29th Australasian Database Conference, ADC 2018, Gold Coast, QLD, Australia, May 24-27, 2018, proceedings. ed. / Junhu Wang; Cong Gao; Jinjun Chen; Jianzhong Qi. Vol. 10837 Champagne, Switzerland: Springer, 2018. p. 174-185.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Child abuse and domestic abuse

T2 - 29th Australasian Database Conference

AU - Subramani, Sudha

AU - Wang, Hua

AU - Islam, Md Rafiqul

AU - Ul-Haq, Anwaar

AU - O'Connor, Manjula

PY - 2018

Y1 - 2018

N2 - Due to increase in popularity of social media, people have started discussing their thoughts and opinions in the form of textual posts. Currently, the people tend to disclose even the socially tabooed topics such as Child Abuse (CA), and Domestic Abuse (DA) to receive the desired response and social support in turn. The increasing volume of abuse related posts being shared on social media is of great interest for public health sectors and family welfare organizations to monitor the public health and promote support services. However, due to the large volume, high velocity and huge variety of context and content of user generated data, it is diﬃcult to mine the diﬀerent kinds of abuse (CA and DA) related posts from other general posts, that ﬂood over the web. Hence, this paper aims to discover and diﬀerentiate the characteristics of CA and DA posts from the massive user generated posts, with the underlying context. Various features such as psycholinguistic, textual and sentimental features are analyzed and Machine Learning techniques are trained to analyze the predictive power of extracted features. Hence, the resulting model achieves more predictive power with high accuracy in classifying possible cases of abuse related posts from diverse user posts.

AB - Due to increase in popularity of social media, people have started discussing their thoughts and opinions in the form of textual posts. Currently, the people tend to disclose even the socially tabooed topics such as Child Abuse (CA), and Domestic Abuse (DA) to receive the desired response and social support in turn. The increasing volume of abuse related posts being shared on social media is of great interest for public health sectors and family welfare organizations to monitor the public health and promote support services. However, due to the large volume, high velocity and huge variety of context and content of user generated data, it is diﬃcult to mine the diﬀerent kinds of abuse (CA and DA) related posts from other general posts, that ﬂood over the web. Hence, this paper aims to discover and diﬀerentiate the characteristics of CA and DA posts from the massive user generated posts, with the underlying context. Various features such as psycholinguistic, textual and sentimental features are analyzed and Machine Learning techniques are trained to analyze the predictive power of extracted features. Hence, the resulting model achieves more predictive power with high accuracy in classifying possible cases of abuse related posts from diverse user posts.

KW - Child Abuse

KW - Domestic Abuse

KW - Social media

KW - Text mining

KW - Machine learning

U2 - 10.1007/978-3-319-92013-9_14

DO - 10.1007/978-3-319-92013-9_14

M3 - Conference paper

SN - 9783319920122

VL - 10837

SP - 174

EP - 185

BT - Databases theory and applications

A2 - Wang, Junhu

A2 - Gao, Cong

A2 - Chen, Jinjun

A2 - Qi, Jianzhong

PB - Springer

CY - Champagne, Switzerland

Y2 - 24 May 2018 through 27 May 2018

ER -

Subramani S, Wang H, Islam MR , Ul-Haq A, O'Connor M. Child abuse and domestic abuse: Content and feature analysis from social media disclosures. In Wang J, Gao C, Chen J, Qi J, editors, Databases theory and applications: 29th Australasian Database Conference, ADC 2018, Gold Coast, QLD, Australia, May 24-27, 2018, proceedings. Vol. 10837. Champagne, Switzerland: Springer. 2018. p. 174-185 doi: 10.1007/978-3-319-92013-9_14

Child abuse and domestic abuse: Content and feature analysis from social media disclosures

Abstract

Conference

UN SDGs

Access to Document

Fingerprint

Cite this