scholarly journals Quantitative Methods for Analyzing Intimate Partner Violence in Microblogs: Observational Study

10.2196/15347 ◽  
2020 ◽  
Vol 22 (11) ◽  
pp. e15347
Author(s):  
Christopher Michael Homan ◽  
J Nicolas Schrading ◽  
Raymond W Ptucha ◽  
Catherine Cerulli ◽  
Cecilia Ovesdotter Alm
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Intimate Partner Violence ◽  
Language Processing ◽  
Partner Violence ◽  
Quantitative Methods ◽  
Intimate Partner ◽  
Support Vector ◽  
Data Set ◽  
Part Of Speech

Background Social media is a rich, virtually untapped source of data on the dynamics of intimate partner violence, one that is both global in scale and intimate in detail. Objective The aim of this study is to use machine learning and other computational methods to analyze social media data for the reasons victims give for staying in or leaving abusive relationships. Methods Human annotation, part-of-speech tagging, and machine learning predictive models, including support vector machines, were used on a Twitter data set of 8767 #WhyIStayed and #WhyILeft tweets each. Results Our methods explored whether we can analyze micronarratives that include details about victims, abusers, and other stakeholders, the actions that constitute abuse, and how the stakeholders respond. Conclusions Our findings are consistent across various machine learning methods, which correspond to observations in the clinical literature, and affirm the relevance of natural language processing and machine learning for exploring issues of societal importance in social media.

scholarly journals Quantitative Methods for Analyzing Intimate Partner Violence in Microblogs: Observational Study (Preprint)

2019 ◽  
Author(s):  
Christopher Michael Homan ◽  
J Nicolas Schrading ◽  
Raymond W Ptucha ◽  
Catherine Cerulli ◽  
Cecilia Ovesdotter Alm
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Intimate Partner Violence ◽  
Language Processing ◽  
Partner Violence ◽  
Quantitative Methods ◽  
Intimate Partner ◽  
Support Vector ◽  
Data Set ◽  
Part Of Speech

BACKGROUND Social media is a rich, virtually untapped source of data on the dynamics of intimate partner violence, one that is both global in scale and intimate in detail. OBJECTIVE The aim of this study is to use machine learning and other computational methods to analyze social media data for the reasons victims give for staying in or leaving abusive relationships. METHODS Human annotation, part-of-speech tagging, and machine learning predictive models, including support vector machines, were used on a Twitter data set of 8767 #WhyIStayed and #WhyILeft tweets each. RESULTS Our methods explored whether we can analyze micronarratives that include details about victims, abusers, and other stakeholders, the actions that constitute abuse, and how the stakeholders respond. CONCLUSIONS Our findings are consistent across various machine learning methods, which correspond to observations in the clinical literature, and affirm the relevance of natural language processing and machine learning for exploring issues of societal importance in social media.

scholarly journals Identification of Intimate Partner Violence from Free Text Descriptions in Social Media

2021 ◽  
Author(s):  
Phan Trinh Ha ◽  
Rhea D'Silva ◽  
Ethan Chen ◽  
Mehmet Koyuturk ◽  
Gunnur Karakurt
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sexual Abuse ◽  
Intimate Partner Violence ◽  
Physical Abuse ◽  
Partner Violence ◽  
Emotional Abuse ◽  
Intimate Partner ◽  
Machine Learning Algorithms ◽  
Free Text

Intimate Partner Violence (IPV) is a significant public health problem that adversely affects the well-being of victims. IPV is often under-reported and non-physical forms of violence may not be recognized as IPV, even by victims. With the increasing popularity of social media and due to the anonymity provided by some of these platforms, people feel comfortable sharing descriptions of their relationship problems in social media. The content generated in these platforms can be useful in identifying IPV and characterizing the prevalence, causes, consequences, and correlates of IPV in broad populations. However, these descriptions are in the form of free text and no corpus of labeled data is available to perform large-scale computational and statistical analyses. Here, we use data from established questionnaires that are used to collect self-report data on IPV to train machine learning models to predict IPV from free text. Using Universal Sentence Encoder (USE) along with multiple machine learning algorithms (Random Forest, SVM, Logistic Regression, Naive Bayes), we develop DETECTIPV, a tool for detecting IPV in free text. Using DETECTIPV, we comprehensively characterize the predictability of different types of violence (Physical Abuse, Emotional Abuse, Sexual Abuse) from free text. Our results show that a general model that is trained using examples of all violence types can identify IPV from free text with area under the ROC curve (AUROC) 89%. We also train type-specific models and observe that Physical Abuse can be identified with greatest accuracy (AUROC 98%), while Sexual Abuse can be identified with high precision but relatively low recall. While our results indicate that the prediction of Emotional Abuse is the most challenging, DETECTIPV can identify Emotional Abuse with AUROC above 80%. These results establish DETECTIPV as a tool that can be used to reliably detect IPV in the context of various applications, ranging from flagging social media posts to detecting IPV in large text corpuses for research purposes. DETECTIPV is available as a web service at https://ipvlab.case.edu/ipvdetect/.

A sentiment analysis system for social media using machine learning techniques: Social enablement

2018 ◽  
Vol 34 (3) ◽  
pp. 569-581 ◽  
Author(s):  
Sujata Rani ◽  
Parteek Kumar
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Media Analysis ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Analysis Tool ◽  
Data Set ◽  
Learning Techniques

Abstract In this article, an innovative approach to perform the sentiment analysis (SA) has been presented. The proposed system handles the issues of Romanized or abbreviated text and spelling variations in the text to perform the sentiment analysis. The training data set of 3,000 movie reviews and tweets has been manually labeled by native speakers of Hindi in three classes, i.e. positive, negative, and neutral. The system uses WEKA (Waikato Environment for Knowledge Analysis) tool to convert these string data into numerical matrices and applies three machine learning techniques, i.e. Naive Bayes (NB), J48, and support vector machine (SVM). The proposed system has been tested on 100 movie reviews and tweets, and it has been observed that SVM has performed best in comparison to other classifiers, and it has an accuracy of 68% for movie reviews and 82% in case of tweets. The results of the proposed system are very promising and can be used in emerging applications like SA of product reviews and social media analysis. Additionally, the proposed system can be used in other cultural/social benefits like predicting/fighting human riots.

scholarly journals Preventing violence by intimate partners in adolescence: an integrative review

2016 ◽  
Vol 50 (1) ◽  
pp. 134-143 ◽  
Author(s):  
Rebeca Nunes Guedes De Oliveira ◽  
Rafaela Gessner ◽  
Bianca de Cássia Alvarez Brancaglioni ◽  
Rosa Maria Godoy Serpa da Fonseca ◽  
Emiko Yoshikawa Egry
Keyword(s):  
Intimate Partner Violence ◽  
Violence Prevention ◽  
Partner Violence ◽  
Quantitative Methods ◽  
Scientific Literature ◽  
Intimate Partner ◽  
Integrative Review ◽  
Public Healthcare ◽  
Healthcare Model ◽  
Psychology And Medicine

Abstract OBJECTIVE To analyze the scientific literature on preventing intimate partner violence among adolescents in the field of health based on gender and generational categories. METHOD This was an integrative review. We searched for articles using LILACS, PubMed/MEDLINE, and SciELO databases. RESULTS Thirty articles were selected. The results indicate that most studies assessed interventions conducted by programs for intimate partner violence prevention. These studies adopted quantitative methods, and most were in the area of nursing, psychology, and medicine. Furthermore, most research contexts involved schools, followed by households, a hospital, a health center, and an indigenous tribe. CONCLUSION The analyses were not conducted from a gender- and generation-based perspective. Instead, the scientific literature was based on positivist research models, intimately connected to the classic public healthcare model and centered on a singular dimension.

#MaybeHeDoesntHitYou: Social Media Underscore the Realities of Intimate Partner Violence

2018 ◽  
Vol 27 (7) ◽  
pp. 885-891 ◽  
Author(s):  
Heather L. McCauley ◽  
Amy E. Bonomi ◽  
Megan K. Maas ◽  
Katherine W. Bogen ◽  
Teagen L. O'Malley
Keyword(s):  
Social Media ◽  
Intimate Partner Violence ◽  
Partner Violence ◽  
Intimate Partner

scholarly journals Intimate partner violence against women: Effects of power distance, individualism and economyKadına yönelik yakın partner şiddeti: Güç mesafesi, bireycilik ve ekonominin etkisi

2016 ◽  
Vol 13 (1) ◽  
pp. 60 ◽  
Author(s):  
Ümran Yüce Selvi ◽  
Derya Karanfil
Keyword(s):  
Intimate Partner Violence ◽  
Partner Violence ◽  
Power Distance ◽  
National Income ◽  
Open Data ◽  
Intimate Partner ◽  
World Health ◽  
Data Set ◽  
Culture Dimensions ◽  
The Relationship

<p>The aim of the present study is to examine the varying rates of physical and sexual intimate partner violence (IPV) across countries with respect to Hofstede's (2001) power distance and individualism culture dimensions and investigate the possible mediating role of country economy in these relationships.  The sample of the study was composed of the values of 25 countries on the study variables. The points of countries on culture dimensions were obtained from Hofstede (2001) open data source. Gross national income per capita (GNIPC) was used as indicator of the economic development of the countries, and the values were taken from World Health Organization report (2013a). Physical and sexual IPV rates of countries were obtained from United Nations Entity for Gender Equality and the Empowerment of Women data set (UN WOMEN, 2011). Countries having points in all three data sets were included in the study. Findings indicated that at cross-cultural level, physical and sexual IPV were significantly and positively correlated with power distance and they were significantly and negatively correlated with individualism and GNIPC. Additionally, mediation analyses showed that GNIPC significantly mediated both the relationship between power distance and physical IPV and power distance and sexual IPV. However, although GNIPC significantly mediated the relationship between individualism and physical IPV, did not mediate the relationship between individualism and sexual IPV.</p><p> </p><p><strong>Özet</strong></p><p><strong></strong>Bu çalışmanın amacı, ülkelerarası farklılaşan fiziksel ve cinsel yakın partner şiddeti (YPŞ) oranlarının, Hofstede (2001)’nin kültürel boyutlarından güç mesafesi ve bireycilik/toplulukçuluk ile ilişkisini incelemek ve ülke ekonomisinin bu ilişkilerdeki olası aracı etkisini saptamaktır. Çalışmanın örneklemi, 25 ülkenin ilgili boyutlardan aldığı değerlerden oluşturmaktadır. Ülkelerin kültür boyutlarındaki değerleri, Hosftede (2001) açık veri setinden elde edilmiştir. Kişi Başına Düşen Gayri Safi Milli Hasıla (GSMH), ülkelerin ekonomik durumunun göstergesi olarak kabul edilmiş ve değerler Dünya Sağlık Örgütü Raporu’ndan (WHO, 2013a) alınmıştır. Çalışmaya dahil edilen ülkelerdeki YPŞ oranları ise, Birleşmiş Milletler Cinsiyet Eşitliği ve Kadınların Güçlendirilmesi Birimi (UN WOMEN, 2011) tarafından derlenen veri setinden elde edilmiştir. Çalışma sonuçları, ülkeler düzeyinde, kadına yönelik fiziksel ve cinsel YPŞ oranlarının, güç mesafesi ile anlamlı düzeyde ve olumlu yönde, bireycilik ve kişi başına düşen GSMH ile anlamlı düzeyde ve olumsuz yönde bir ilişkisinin olduğu ortaya koymuştur. Aracı etki analizleri, kişi başına düşen GSMH’nın güç mesafesi ile fiziksel ve cinsel YPŞ ve bireycilik ile fiziksel YPŞ ilişkisine aracılık ettiğini; buna karşın bireycilik ile cinsel YPŞ ilişkisine aracılık etmediğini göstermiştir.</p>

scholarly journals Sentiment Analysis on Social Media Big Data With Multiple Tweet Words

2019 ◽  
Vol 8 (10) ◽  
pp. 3429-3434 ◽  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Big Data ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Sentiment Classification ◽  
Support Vector ◽  
Decision Tree Classifier ◽  
Machine Learning Classification ◽  
Tree Classifier

The main objective of this paper is Analyze the reviews of Social Media Big Data of E-Commerce product’s. And provides helpful result to online shopping customers about the product quality and also provides helpful decision making idea to the business about the customer’s mostly liking and buying products. This covers all features or opinion words, like capitalized words, sequence of repeated letters, emoji, slang words, exclamatory words, intensifiers, modifiers, conjunction words and negation words etc available in tweets. The existing work has considered only two or three features to perform Sentiment Analysis with the machine learning technique Natural Language Processing (NLP). In this proposed work familiar Machine Learning classification models namely Multinomial Naïve Bayes, Support Vector Machine, Decision Tree Classifier, and, Random Forest Classifier are used for sentiment classification. The sentiment classification is used as a decision support system for the customers and also for the business.

scholarly journals Changes in intimate partner violence during the early stages of the COVID-19 pandemic in the USA

2020 ◽  
pp. injuryprev-2020-043831 ◽  
Author(s):  
Katelyn K Jetelina ◽  
Gregory Knell ◽  
Rebecca J Molsberry
Keyword(s):  
Social Media ◽  
Intimate Partner Violence ◽  
Partner Violence ◽  
Regression Models ◽  
Job Loss ◽  
Physical Violence ◽  
Intimate Partner ◽  
Early States ◽  
Early Stages ◽  
The Usa

The objective of this study is to describe intimate partner violence (IPV) severity and types of victimization during the early states of the COVID19 pandemic. A survey was distributed through social media and email distribution lists. The survey was open for 14 days in April 2020 and 2441 participated. Information on IPV, COVID19-related IPV severity, sociodemographics, and COVID19-related behaviors (eg, job loss) were collected. Regression models were used to evaluate COVID19-related IPV severity across victimization types and sociodemographics. 18% screened positive for IPV. Among the respondents that screened positive, 54% stated the victimization remained the same since the COVID19 outbreak, while 17% stated it worsened and 30% stated it got better. The odds of worsening victimization during the pandemic was significantly higher among physical and sexual violence. While the majority of IPV participants reported victimization to remain the same, sexual and physical violence was exacerbated during the early stages of the pandemic. Addressing victimization during the pandemic (and beyond) must be multi-sectorial.

scholarly journals Feasibility Study of Social Media to Reduce Intimate Partner Violence Among Gay Men in Metro Atlanta, Georgia

2013 ◽  
Vol 13 (3) ◽  
pp. 298-304 ◽  
Author(s):  
Sheryl Strasser ◽  
Megan Smith ◽  
Danielle Pendrick-Denney ◽  
Sarah Boos-Beddington ◽  
Ken Chen ◽  
...  
Keyword(s):  
Social Media ◽  
Intimate Partner Violence ◽  
Gay Men ◽  
Feasibility Study ◽  
Partner Violence ◽  
Intimate Partner

Viral justice? Online justice-seeking, intimate partner violence and affective contagion

2018 ◽  
Vol 23 (3) ◽  
pp. 375-393 ◽  
Author(s):  
Mark Wood ◽  
Evelyn Rose ◽  
Chrissy Thompson
Keyword(s):  
Social Media ◽  
Intimate Partner Violence ◽  
Partner Violence ◽  
Intimate Partner ◽  
Key Dimensions

What has been termed the survivor selfie is a recent and growing phenomenon whereby survivors of intimate partner violence or their close supporters upload graphic photos and accounts of their injuries and suffering to social media. In this article, we examine how the like economy of Facebook can lead to the rapid circulation of survivor selfies to large audiences, and in doing so, generate what we term viral justice: the outcome of a victim’s online justice-seeking post ‘going viral’ and quickly being viewed and shared-on by thousands of social media users. Through examining the trajectory and impact of one particular case—Ashlee Savins’s viral survivor selfie—we identify the technological preconditions of viral justice and three of its key dimensions: affective contagion; swarm sociality; and movement power. Through discussing the speed, sociality and contagion of viral justice, we critically consider some of its implications for online justice-seeking, and responding to intimate partner violence.

Sign in / Sign up

Export Citation Format

Share Document