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/.

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.

Intimate Partner Violence

2019 ◽  
Author(s):  
Jane S. Sillman
Keyword(s):  
Risk Factors ◽  
Sexual Abuse ◽  
Intimate Partner Violence ◽  
Physical Abuse ◽  
Partner Violence ◽  
Elder Abuse ◽  
Violent Behavior ◽  
Intimate Partner ◽  
Violence Risk ◽  
Gay Couples

Intimate-partner violence describes relationships characterized by intentional controlling or violent behavior by someone who is in an intimate relationship with the victim. The abuser’s controlling behavior may take many forms, including psychological abuse, physical abuse, sexual abuse, economic control, and social isolation. Abuse may ultimately lead to the death of the victim from homicide or suicide. Typically, an abusive relationship goes through cycles of violence. There are periods of calm, followed by increasing tension in the abuser, outbursts of violence, and return to periods of calm. These cycles often spiral toward increasing violence over time. The victims of intimate-partner violence are usually women, but intimate-partner violence is also a significant problem for gay couples and for the disabled and elderly of both sexes. This review discusses the epidemiology, diagnosis, treatment, outcomes, and prevention of intimate-partner violence. Risk factors for experiencing violence, risk factors for perpetrating violence, and consequences of abuse are also analyzed. This review contains 5 figures, 14 tables, and 30 references. Keywords: Domestic abuse, intimate-partner violence, elder abuse, child abuse, batterer, sexual abuse, physical abuse

Intimate Partner Violence and Material Hardship Among Urban Mothers

2019 ◽  
Vol 26 (9) ◽  
pp. 935-954 ◽  
Author(s):  
Julia O’Connor ◽  
Lenna Nepomnyaschy
Keyword(s):  
Intimate Partner Violence ◽  
Physical Abuse ◽  
Partner Violence ◽  
Emotional Abuse ◽  
Fixed Effects ◽  
Population Based ◽  
Intimate Partner ◽  
Time Varying ◽  
Material Hardship ◽  
Urban Mothers

Using a longitudinal population-based sample ( n = 4,234), this study explored the association of intimate partner violence (IPV) with material hardship. We found that women who experienced IPV are substantially more likely to experience material hardship, even after controlling for a comprehensive set of static and time-varying characteristics, including material hardship at the prior wave and individual fixed effects. Associations were strongest for experiences of physical abuse (the least prevalent type of IPV) and controlling abuse (the most prevalent type of IPV) but were weaker for emotional abuse. Results suggest that IPV increases the probability of material hardship by 10-25%.

Intimate Partner Violence

2019 ◽  
Author(s):  
Jane S. Sillman
Keyword(s):  
Risk Factors ◽  
Sexual Abuse ◽  
Intimate Partner Violence ◽  
Physical Abuse ◽  
Partner Violence ◽  
Elder Abuse ◽  
Violent Behavior ◽  
Intimate Partner ◽  
Violence Risk ◽  
Gay Couples

Intimate-partner violence describes relationships characterized by intentional controlling or violent behavior by someone who is in an intimate relationship with the victim. The abuser’s controlling behavior may take many forms, including psychological abuse, physical abuse, sexual abuse, economic control, and social isolation. Abuse may ultimately lead to the death of the victim from homicide or suicide. Typically, an abusive relationship goes through cycles of violence. There are periods of calm, followed by increasing tension in the abuser, outbursts of violence, and return to periods of calm. These cycles often spiral toward increasing violence over time. The victims of intimate-partner violence are usually women, but intimate-partner violence is also a significant problem for gay couples and for the disabled and elderly of both sexes. This review discusses the epidemiology, diagnosis, treatment, outcomes, and prevention of intimate-partner violence. Risk factors for experiencing violence, risk factors for perpetrating violence, and consequences of abuse are also analyzed. This review contains 5 figures, 14 tables, and 30 references. Keywords: Domestic abuse, intimate-partner violence, elder abuse, child abuse, batterer, sexual abuse, physical abuse

Social Support as a Mediator of Revictimization of Low-Income African American Women

2003 ◽  
Vol 18 (4) ◽  
pp. 419-431 ◽  
Author(s):  
Marnette Bender ◽  
Sarah Cook ◽  
Nadine Kaslow
Keyword(s):  
Social Support ◽  
Sexual Abuse ◽  
Intimate Partner Violence ◽  
African American ◽  
African American Women ◽  
Low Income ◽  
Childhood Maltreatment ◽  
Partner Violence ◽  
Emotional Abuse ◽  
Intimate Partner

Mediating effects of social support on the link between childhood maltreatment and adult intimate partner violence (IPV) were explored in a sample of 362 low-income, African American women. We examined relations between childhood maltreatment experiences (total maltreatment, sexual abuse, physical abuse, emotional abuse, emotional neglect, and physical neglect) and adult maltreatment (physical IPV and nonphysical IPV). Results of hierarchical multiple regression analyses revealed small, but significant, effects. Further, social support mediated revictimization. Social support fully mediated relations in which the form of childhood maltreatment was different than the form of adult IPV (e.g., the relation between childhood sexual abuse and adult nonphysical IPV), but only partially mediated the relations in which the form of childhood maltreatment was similar to adult IPV (e.g., the relation between childhood emotional abuse and adult nonphysical IPV). Implications for clinical interventions for women with intimate partner violence experiences are discussed.

scholarly journals Sexual and physical intimate partner violence among women using antenatal care in Nampula, Mozambique

2018 ◽  
Author(s):  
Eusébio Chaquisse ◽  
Sílvia Fraga ◽  
Paula Meireles ◽  
Glória Macassa ◽  
Joaquim Soares ◽  
...  
Keyword(s):  
Sexual Abuse ◽  
Intimate Partner Violence ◽  
Antenatal Care ◽  
Physical Abuse ◽  
Alcohol Drinking ◽  
Partner Violence ◽  
Cross Sectional Study ◽  
Intimate Partner ◽  
Cross Sectional ◽  
Physical Intimate Partner Violence

The aim was to estimate the prevalence of sexual and physical intimate partner violence (IPV) and its associated factors, in a sample of pregnant women using antenatal care (ANC) in Nampula province - Mozambique. This cross-sectional study was carried out in six health units in Nampula, from February 2013 to January 2014. Overall, 869 participants answered the Conflict Tactics Scale 2. The lifetime and past year prevalence of sexual abuse was 49% and 46%, and of physical abuse was 46% and 44%, respectively. Lifetime and past year sexual abuse was significantly associated with living as a couple, alcohol drinking and having a past diagnosis of gonorrhea. Lifetime and past year physical abuse increased significantly with age and was associated with living as a couple, alcohol drinking and history with syphilis. The prevalence of lifetime and previous year violence among women using ANC was high and similar showing that most women were constantly exposed to IPV. ANC provides a window of opportunity for identifying and acting on violence against women.

scholarly journals Childhood Trauma and Dissociative Intimate Partner Violence

2018 ◽  
Vol 25 (2) ◽  
pp. 148-166 ◽  
Author(s):  
Aliya R. Webermann ◽  
Christopher M. Murphy
Keyword(s):  
Sexual Abuse ◽  
Intimate Partner Violence ◽  
Childhood Abuse ◽  
Childhood Trauma ◽  
Partner Violence ◽  
Emotional Abuse ◽  
Emotion Dysregulation ◽  
Intimate Partner ◽  
Abusive Behavior ◽  
Abusive Men

The present study assesses childhood abuse/neglect as a predictor of dissociative intimate partner violence (IPV) among 118 partner-abusive men. One third (36%) endorsed dissociative IPV, most commonly losing control (18%), surroundings seeming unreal (16%), feeling someone other than oneself is aggressing (16%), and seeing oneself from a distance aggressing (10%). Childhood physical abuse/neglect predicted IPV-specific derealization/depersonalization, aggressive self-states, and flashbacks to past violence. Childhood emotional abuse/neglect predicted derealization/depersonalization, blackouts, and flashbacks. Childhood sexual abuse uniquely predicted amnesia. Other potential traumas did not predict dissociative IPV, suggesting dissociative IPV is influenced by trauma-based emotion dysregulation wherein childhood abuse/neglect survivors disconnect from their abusive behavior.

The Association of Partner Abuse Types and Suicidal Ideation Among Men and Women College Students

2016 ◽  
Vol 31 (3) ◽  
pp. 471-485 ◽  
Author(s):  
Caitlin Wolford-Clevenger ◽  
Noelle C. Vann ◽  
Phillip N. Smith
Keyword(s):  
College Students ◽  
Gender Differences ◽  
Intimate Partner Violence ◽  
Suicidal Ideation ◽  
Physical Abuse ◽  
Partner Violence ◽  
Emotional Abuse ◽  
Intimate Partner ◽  
The Impact ◽  
Women Clinicians

Despite the well-documented relations between intimate partner violence and suicidal ideation, gender differences regarding the relationships between intimate partner violence types and suicidal ideation are less understood. In addition, few studies have examined the risk that harassment may confer for suicidal ideation in the context of intimate partner violence. This study examined gender differences in the associations of harassment, emotional, and physical intimate partner violence with suicidal ideation in 502 college students, while controlling for the influence of depressive symptoms. Results indicated that physical abuse, but not harassment or emotional abuse, was associated with increased suicidal ideation in men. In contrast, emotional abuse, but not physical abuse or harassment, was associated with increased suicidal ideation in women. Clinicians should consider potential gender differences in the impact of intimate partner violence on suicidal ideation when assessing suicide risk.

Intimate Partner Violence

2019 ◽  
Author(s):  
Jane S. Sillman
Keyword(s):  
Risk Factors ◽  
Sexual Abuse ◽  
Intimate Partner Violence ◽  
Physical Abuse ◽  
Partner Violence ◽  
Elder Abuse ◽  
Violent Behavior ◽  
Intimate Partner ◽  
Violence Risk ◽  
Gay Couples

Intimate-partner violence describes relationships characterized by intentional controlling or violent behavior by someone who is in an intimate relationship with the victim. The abuser’s controlling behavior may take many forms, including psychological abuse, physical abuse, sexual abuse, economic control, and social isolation. Abuse may ultimately lead to the death of the victim from homicide or suicide. Typically, an abusive relationship goes through cycles of violence. There are periods of calm, followed by increasing tension in the abuser, outbursts of violence, and return to periods of calm. These cycles often spiral toward increasing violence over time. The victims of intimate-partner violence are usually women, but intimate-partner violence is also a significant problem for gay couples and for the disabled and elderly of both sexes. This review discusses the epidemiology, diagnosis, treatment, outcomes, and prevention of intimate-partner violence. Risk factors for experiencing violence, risk factors for perpetrating violence, and consequences of abuse are also analyzed. This review contains 5 figures, 14 tables, and 30 references. Keywords: Domestic abuse, intimate-partner violence, elder abuse, child abuse, batterer, sexual abuse, physical abuse

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.

Sign in / Sign up

Export Citation Format

Share Document