scispace - formally typeset
Search or ask a question

What are the different ways to classify bullying severity? 


Best insight from top research papers

Different ways to classify bullying severity include evaluating texts using Support Vector Machine (SVM) classifiers and developing a Fuzzy Logic System that uses the outputs of SVM classifiers as inputs . Another approach is to develop a feature-based model that uses features from the content of a tweet to classify tweets as non-cyberbullied, and low, medium, or high-level cyberbullied tweets . Additionally, a cyberbullying detection framework can be used to generate features from Twitter content and develop a supervised machine learning solution for cyberbullying detection and multi-class categorization of its severity . Furthermore, severity can be associated with bullying involvement in children with chronic health conditions, with condition severity being a risk factor for bullying involvement . Lastly, the Bullying Situations Identification Instrument (BSI) identifies three dimensions of bullying severity: social/emotional, physical, and verbal .

Answers from top 4 papers

More filters
Papers (4)Insight
The paper identifies three dimensions of bullying severity: social/emotional, physical, and verbal.
Open accessJournal ArticleDOI
Bandeh Ali Talpur, Declan O'Sullivan 
27 Oct 2020-PLOS ONE
40 Citations
The paper proposes a machine learning framework for classifying cyberbullying severity into different levels using Naive Bayes, KNN, Decision Tree, Random Forest, and Support Vector Machine algorithms.
The paper classifies bullying severity into three levels: low, medium, and high. Different features such as age group, personality type, and tweet engagement are used to determine the severity.
The paper proposes a framework that uses Support Vector Machine (SVM) classifiers and a Fuzzy Logic System to determine bullying severity in texts.

Related Questions

How does immigrant population differentiated in bullying studies?4 answersImmigrant populations are often highlighted in bullying studies due to their unique experiences. Research indicates that immigrant youth face increased exposure to school bullying, including discrimination and harassment, possibly due to perceptions of low academic ability and fear of safety. Studies show that immigrant parents, compared to non-immigrant parents, are more satisfied with schools but face challenges in relations with other parents, emphasizing vulnerability and ethnicity-based bullying as crucial areas for attention. Additionally, very-low-income immigrant adolescents are at a higher risk of victimization, with peer friendship acting as a protective factor against bullying, especially for natives, while peer acceptance may pose a risk, particularly for bullying in natives. Furthermore, migrant children exhibit a higher prevalence of school bullying, with factors like gender, grade, violent game exposure, social connections, and parental abuse influencing their involvement in bullying. Anti-immigrant prejudices play a significant role in racial bullying, highlighting the need to address prejudice in interventions.
What are the legal definitions and classifications of bullying in different countries?5 answersBullying is defined and classified differently across various countries. In European states, bullying legislation varies, with criminal liability not specifically for bullying but for related offenses like stalking, harassment, and hate crimes. Workplace bullying, a form of aggression, occurs globally, leading to legal dilemmas and health issues. Countries like the UK, Canada, Australia, and the USA have laws addressing workplace bullying, treating it as a dignity violation, harassment, or health and safety concern. Workplace bullying is often described as persistent mistreatment with a power imbalance, encompassing behaviors like verbal abuse, intimidation, and sabotage. Cyberbullying, a modern challenge, adds complexity to the legal framework, necessitating continuous adaptation of laws to combat this detrimental phenomenon.
How to compute severity index?4 answersTo compute a severity index, different methodologies and scales are used depending on the context. In the context of existing buildings, a methodology based on a distribution of values and a single scalar is proposed to calculate the severity index of damages in buildings. This methodology is easy to use and flexible. In the context of disease outbreaks, a severity index is created using metrics related to case morbidity/mortality, outbreak duration, and their ratios. The index scores are generated by averaging complete metrics per outbreak, allowing for the comparison of outbreak severity. In the context of voltage stability, a three-layer voltage stability index is computed using time-series obtained from dynamic simulations. The index provides information about violations of power and voltage limits in a system. In the context of plant diseases, a disease severity index (DSI) is calculated using an ordinal scale based on the percent area with symptoms. The DSI estimates the severity of the disease and can be influenced by the method used for calculation and the nature of the ordinal scale. In the context of humanitarian crises, the INFORM Severity Index is used to estimate the severity of a crisis based on publicly available indicators. The index is refined using factor analysis to better quantify crisis severity.
What are the types of bullying?5 answersBullying can take various forms, including physical, verbal, relational, and cyber bullying. Physical bullying involves acts such as hitting, pushing, or tripping someone. Verbal bullying includes mocking, name-calling, and making fun of someone's physical appearance or weaknesses. Relational bullying involves actions that aim to harm someone's social relationships, such as spreading rumors or excluding them from social groups. Cyber bullying occurs through electronic means, such as sending hurtful messages or spreading rumors online. These different types of bullying can have negative impacts on the victims, leading to mental, emotional, and physical consequences. It is important to address and prevent all forms of bullying to create a safe and supportive environment for children and adolescents.
What are the most effective ways to classify attacks in critical infrastructure?5 answersOne of the most effective ways to classify attacks in critical infrastructure is through the use of machine learning techniques, specifically deep learning-based methods. These methods involve constructing new representations and modeling the system behavior using multilayer autoencoders. By capturing the physical relationships among the measurements, these representations have more discriminant power in distinguishing the location of the attack. Additionally, combining deep learning with other techniques such as genetic algorithms for optimal feature selection can further improve the accuracy of intrusion detection systems. These methods have been shown to outperform conventional machine learning models in various cyber-attack scenarios.
What are the types of bullying ?3 answersBullying can take various forms, including physical, verbal, relational, and cyberbullying. Physical bullying involves assault, property destruction, and physical harm. Verbal bullying includes hurtful or demeaning speech, threats, and mocking. Relational bullying focuses on undermining reputation or relationships. Cyberbullying involves the use of technology or the internet to intimidate or harm others. These different types of bullying can have lasting consequences for both victims and perpetrators.

See what other people are reading

How does tiktok algorithm affect human brain?
5 answers
The TikTok algorithm significantly impacts the human brain in various ways. Research highlights that TikTok's algorithmic environment influences users' internal states, leading to addiction behaviors. Additionally, TikTok's addictive nature is acknowledged, with users utilizing the app as a means of distraction and escape in daily life. The platform's user-centered algorithm recommendation mode enhances content reception convenience and pleasure, affecting users, especially the younger generation, by creating an information cocoon effect that limits exposure to diverse content. Moreover, the affective flows of misinformation on TikTok, particularly in Conspiracy TikTok, underscore the critical role of algorithmic personalization in shaping user experiences and perceptions. Overall, TikTok's algorithm plays a pivotal role in shaping user behaviors, emotions, and information consumption patterns.
How to classifier breed horse?
5 answers
To classify horse breeds, various methods have been explored in recent research. One effective approach is the use of deep learning techniques, specifically pre-trained deep convolutional neural networks, which have shown promising results in automatic breed classification of horses. Another method involves utilizing a neuro-fuzzy classifier (NFC) of the Takagi-Sugeno-Kang (TSK) type, combined with wavelet packet (WP) transformed data, to classify different horse gaits based on rider's hip motion data collected by inertial sensors. Additionally, genetic information and classification algorithms have been employed to investigate genetic relationships and population structure among different horse breeds, demonstrating the utility of machine learning algorithms like Naive Bayes and IB1 for breed discrimination tasks. Furthermore, a study utilized a combination of wireless motion sensors and machine learning to automatically classify horse gaits with high accuracy, enabling detailed biomechanical studies and genetic research in gait classification.
What are the psychological factors that contribute to the fear of missing out (FOMO)?
4 answers
Psychological factors contributing to the Fear of Missing Out (FOMO) include social comparison theory, self-determination theory, and uses and gratifications theory. Anonymity on social media platforms has been found to moderate the relationship between FOMO and psychological well-being, with individuals using anonymous accounts experiencing a negative association between FOMO and well-being. Additionally, the restlessness caused by the dependence on social networks can lead to FOMO, affecting psychological well-being. FOMO is described as a negative affect stemming from feelings of being excluded from rewarding experiences, and it can be both a dispositional trait and a behavioral state influenced by situational factors. These factors collectively contribute to the development and impact of FOMO on individuals' psychological well-being.
How does AI technology specifically affect various aspects of a student's academic performance?
5 answers
AI technology significantly impacts various aspects of a student's academic performance. It plays a crucial role in predicting student performance, automating evaluations, and enhancing teaching quality through assessment activities. AI tools like neural networks and natural language processing help in making evaluations more objective and automating the process, while educational robots analyze the learning process to improve student assessment. Additionally, the application of fuzzy logic and fuzzy expert systems aids in student allocation, which influences academic performance by optimizing student groupings based on imprecise judgments. However, the introduction of AI can also lead to negative impacts such as loss of human decision-making, laziness, and privacy concerns among students, emphasizing the need for careful implementation and addressing of these issues before integrating AI technologies into education systems.
What factors are considered when evaluating the validity and reliability of a selection process for restaurant managers?
5 answers
When evaluating the validity and reliability of a selection process for restaurant managers, factors such as health concerns influencing restaurant selection, the importance of criteria in customer decisions, and the characteristics of the recruitment and selection process in the food and beverages industry are crucial. The validity and reliability of selection methods play a significant role in predicting job performance. Additionally, the criteria influencing customer decisions in restaurant selection are essential, with methods like IVIF-CRITIC and IVIF-CoCoSo being used to rank restaurants based on these criteria. Moreover, the specific recruitment and selection process in the food and beverages industry involve various tests and indicators to evaluate candidates thoroughly. These factors collectively contribute to ensuring a valid and reliable selection process for restaurant managers.
What are the specific advantages of collecting and analyzing restaurant data for businesses?
5 answers
Collecting and analyzing restaurant data offers several advantages for businesses. Firstly, it allows for the quantification of food waste, aiding in setting quality baselines and tracking changes over time in different hospitality segments. Secondly, technological innovations like tableside ordering provide insights into customer behavior, preferences, and trends, enhancing marketing strategies and optimizing operations. Additionally, utilizing ensemble machine learning in digital marketing can lead to accurate predictions, improved recommendations, and cost reduction in the food delivery business. Moreover, studying the association between restaurant access and weight-related outcomes can provide valuable insights for businesses targeting children and adolescents, contributing to better-informed decisions regarding menu quality and customer offerings. Lastly, analyzing the nutrition environment in restaurants and its impact on children's diet quality and anthropometrics can guide businesses in creating healthier food environments and offerings.
What are the different theories and approaches to measuring satisfaction?
5 answers
Various theories and approaches exist for measuring satisfaction. The grey fuzzy theory is utilized to design a customer satisfaction measurement system with improved timeliness. Relative deprivation and relative satisfaction concepts focus on individual-level indicators, emphasizing utility from a relativistic perspective. The MUSA method presents a multicriteria evaluation approach for customer satisfaction, employing collective preference disaggregation and ordinal regression analysis. In the context of e-learning, customer satisfaction is crucial, with methods like factor and cluster analysis used to assess student satisfaction levels. Additionally, satisfaction measurement in music education involves assessing various aspects like studies, teaching staff, and facilities through qualitative and quantitative research methods. These diverse theories and approaches offer valuable insights into understanding and evaluating satisfaction across different domains.
Issues and challenges of machine learning in medical field
5 answers
Machine learning (ML) in the medical field faces several challenges. These include the need for proper evaluation and maintenance of ML models due to data drift, the difficulty in widely accepting ML results in clinical settings, and the necessity to rapidly learn from vast medical data for accurate predictions and decision support. Additionally, the emergence of computational medicine and big data has highlighted the importance of extracting valuable information efficiently from biomedical data. Despite the advantages of deep learning in automating feature extraction from complex biological data, challenges like data interpretability and privacy persist. Overall, the integration of machine learning tools in healthcare aims to enhance traditional services, automate diagnoses, and provide quick medical advice, but challenges like data privacy and interpretability need to be addressed for wider adoption.
How can make python script?
5 answers
To create a Python script, one can utilize various methods and tools outlined in the provided research contexts. One approach involves leveraging the Fuzzy Time Series Markov Chain model in Python to forecast cocoa plant diseases efficiently. Another method highlighted is the utilization of scripts for groundwater modeling and data analysis, emphasizing the advantages of reproducibility and error detection in modeling processes. Additionally, a script generation method using Python is detailed, enhancing the efficiency of script creation and ensuring a specified format. Moreover, the development of a Python script for automatic data cleaning and labeling is discussed, showcasing the use of machine learning techniques for enhancing data quality and analysis. Lastly, the importance of scripting with Python for computational scientists is emphasized, focusing on productivity, reliability, and open-source tools for tailored working environments.
How effective are support vector machines (SVMs) in accurately classifying sentiment in text-based data?
5 answers
Support Vector Machines (SVMs) have shown effectiveness in accurately classifying sentiment in text-based data. Various studies have highlighted SVMs' performance in sentiment analysis tasks. SVMs, when combined with feature selection techniques like PSO and Information Gain, have demonstrated significant accuracy improvements, reaching up to 86.81% accuracy. Additionally, SVMs paired with fuzzy matching (FM) for dimensionality reduction achieved a high accuracy rate of 96% in sentiment analysis tasks. Despite their power in sentiment classification, SVMs are noted for their slow training speed, prompting the need for efficient optimization methods to enhance their performance. Furthermore, SVMs, when integrated with TF-IDF and Recursive Feature Elimination, have outperformed existing techniques in sentiment classification, showcasing accuracy rates of 88% and 84.5% in different datasets. These findings collectively underscore SVMs' effectiveness in accurately classifying sentiment in text-based data.
Can mindfulness be measured by qualitatively and quantitatively?
4 answers
Mindfulness can indeed be measured both qualitatively and quantitatively. Various research papers have developed scales and measures to assess different aspects of mindfulness. For instance, the development of observer-report questionnaires like the Observed Mindfulness Measure (OMM) allows for the qualitative assessment of mindfulness behaviors noticeable to others. On the other hand, scales like the Mindfulness Adherence Questionnaire (MAQ) provide a quantitative assessment by evaluating the quantity and quality of formal and informal mindfulness practice. Additionally, the Applied Mindfulness Process Scale (AMPS) quantifies the level of applying mindfulness skills during and after interventions, showcasing the behavioral aspects associated with therapeutic change. These diverse measures collectively contribute to a comprehensive evaluation of mindfulness through both qualitative and quantitative lenses.