Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Stereotype Content Model02:16

Stereotype Content Model

15.2K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.2K
Force Classification01:22

Force Classification

2.1K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.1K
Actor-Observer Effect01:23

Actor-Observer Effect

183
The actor-observer effect, a cognitive bias closely linked to the fundamental attribution error, refers to the tendency for individuals to attribute their behavior to external, situational factors while explaining others’ behavior in terms of internal, dispositional traits. This asymmetry in attribution significantly influences social perception and judgment.Cognitive Mechanisms Behind the EffectTwo primary psychological mechanisms contribute to the actor-observer effect: differences in...
183
Role of Emotions in Social Life01:01

Role of Emotions in Social Life

250
Emotions play a fundamental role in shaping human experience and interactions. The absence of emotions would render life incomplete and fail to capture the essence of human nature. In social psychology, feelings and moods have been extensively studied due to their profound impact on social life and interpersonal relationships. These affective states influence decision-making, behavior, and social perceptions, making them integral to understanding human interactions.Emotions and Social...
250
Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

146
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
146
Role-Based Identity01:21

Role-Based Identity

115
Role-based identities are central to understanding how individuals navigate social environments by adopting distinct self-conceptions aligned with various societal roles. These identities are not fixed traits but are constructed through personal actions and the social feedback individuals receive in context-specific interactions. Each social role, such as student, teacher, or friend, carries a set of expectations and norms that influence how people think, feel, and behave within that...
115

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Post-Acute Care Pathways After Sexual Violence and Intimate Partner Violence: An International Health-Services Scoping Review with Implications for Italy.

Healthcare (Basel, Switzerland)·2026
Same author

Gender-based violence against women and girls aged ≥15 years presenting to European emergency departments: a multinational, cross-sectional analysis.

The Lancet. Public health·2026
Same author

Adolescent non-suicidal self-injury, contextual and area-level inequalities: Insights from ten years of emergency department visits in northern Italy.

Public health·2026
Same author

Factors associated with long-term survival after traumatic and non-traumatic spinal cord injury: a 12-year population-based retrospective cohort study in Italy.

Spinal cord·2025
Same author

EpiCHILD assessment tool: identifying exposure to witnessed violence in children and adolescents.

Annali dell'Istituto superiore di sanita·2025
Same author

Confusion Assessment Protocol: Italian Cross-Cultural Adaptation and Validation.

Brain sciences·2025

Related Experiment Video

Updated: Dec 5, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

401

Violence detection explanation via semantic roles embeddings.

Enrico Mensa1, Davide Colla1, Marco Dalmasso2

  • 1Department of Computer Science, University of Turin, Corso Svizzera 185, Turin, 10149, Italy.

BMC Medical Informatics and Decision Making
|October 16, 2020
PubMed
Summary

A new system, VIDES (VIOLENCE DETECTION SYSTEM), accurately detects violence-related injuries from emergency room reports using deep learning. This helps track and prevent violence by analyzing medical texts for injury indicators.

Keywords:
Categorization explanationEvent extractionExplanationSemantic framesSlot fillingText categorizationViolent event trackingWord embeddingsXAI

Related Experiment Videos

Last Updated: Dec 5, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

401

Area of Science:

  • Natural Language Processing
  • Artificial Intelligence in Medicine
  • Public Health Informatics

Background:

  • Emergency room reports are challenging for NLP, often under-reporting violence against vulnerable groups.
  • Accurate categorization of violence-related injuries (V) versus non-violence-related injuries (NV) is crucial for developing violence-tracking and prevention systems.
  • Identifying specific elements within reports that indicate violence is a key challenge.

Purpose of the Study:

  • To develop and validate a system (VIOLENCE DETECTION SYSTEM - VIDES) for detecting violence episodes from narrative emergency room reports.
  • To improve the accuracy of identifying violence-related injuries in clinical narratives.
  • To enhance the interpretability of AI systems in the medical domain by combining different representational techniques.

Main Methods:

  • Employed a deep neural network for categorizing emergency room reports.
  • Developed a novel hybrid technique for semantic frame-filling, integrating distributed term representations with syntactic and semantic information.
  • Validated the system on a dataset of over 150,000 annotated records for violence (V/NV) and 200 records with detailed semantic role annotations (e.g., agent, victim).

Main Results:

  • The VIDES system achieved high precision and recall for categorizing negative cases (non-violence) and strong performance on positive cases (.97 precision, .94 recall).
  • Accuracy in recognizing specific semantic roles related to violence varied from .28 to .90.
  • The system successfully identified annotation errors made by hospital staff in the dataset.

Conclusions:

  • The VIDES system demonstrates the effectiveness of combining distributed and symbolic (frame-like) representations for interpretable AI in medical text analysis.
  • The proposed methodology offers a generalizable approach for enhancing AI interpretability across various application areas and categorization tasks.
  • This work contributes to better tracking and prevention of violence by improving the analysis of clinical narratives.