International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 07 | July 2022
www.irjet.net
p-ISSN: 2395-0072
Semantic Sentiment Analysis using Machine Learning for Suicidal Tendency Prediction from Social Network Ashrita Shivananda Hegde1, Dhanushree B2, Kavana L3, Thanushree K A4, Vimuktha E Salis5 1,2,3,4Students,
Department of Information Science & Engineering, Global Academy of Technology, Bengaluru, India Professor, Department of Computer Science & Engineering, Global Academy of Technology, Bengaluru, India --------------------------------------------------------------------***--------------------------------------------------------------------Abstract - Withtheincrease insocial networkingspots, 2. REVIEW OF LITERATURE 5Associate
people are nowmore engaged in their virtual livesthan ever ahead and at the same time, the number of information people puts online is enormous, offering experimenters an inestimable tool for conducting exploration. People tend to put theirstudies onlinetopartakewiththewholeworldwhich alsoincludes suicidalstudies. Self-murderis a social problem and is a major concern in recent times.
This chapter evaluates the current work with the previous one. It depicts the current implementation that overcomes the previous problem and limitation of the problem and the plans to build the project and scope of the project.
2.1 A Machine Learning Approach to Analyze and Predict Suicide Attempts,2021
Moment, people witnessseverephysicaldiseasesandcerebral stress due to a variety of internal and external factors. Although depression is substantially planted in people in their 30s and 40s, it's frequently detected in kids due to academic stress and interpersonal relationships and in seniors. In India, there are social causes as well that promote self-murder attempts, the most common being dowry controversies. A lot of vituperative content, importunity, gibing, and cyberbullying affiliated conditioning has come veritably common on similar platforms which have dangerous goods on a person’s internal and cerebral health. This can occasionally lead to mischievous and life-long traumatic goods on an existent.
Data Analysis is carried out, in order to classify data so as to give a set of preventative measures to control them in the future. This can give information about the cause of selfmurder taken in a particular state followed by in a particular time. The dataset can alsogive information about whether the self-murder rate for a particular cause has increased or not. Our end is to find a machine literacy model for the vaticination ofself-murder attempts. Logistic retrogression, Decision trees, grade Boosted Decision Trees, Support Vector Machines, and Artificial Neural Networks are some of the models used.
2.2 Automatic identification of suicide notes with a transformer-based deep learning model,2021
Key Words: Sentiment analysis, NLP, NLTK, Chatbot 1.INTRODUCTION
In this paper, we use the motor encoder to model the input textbook. The motor encoder armature contains the following factors multi-head tone-attention subcaste, completely connected feed-forward network, subcaste normalization, and positional encodings. The general armature is shown as a light green block. originally, the positional encodings are added to the input embeddings to ensure that the model takes advantage of the word-order or fixed successional information, including relative and absolute positional information since there's no complication or rush. In this work, we use sine and cosine functions of different frequentness proposed by Gehring to get positional encodings.
Self-murder has been an intractable public health problem despite advances in the opinion and treatment of major internal diseases. A growing area is the development of self-murder webbing technologies through penetrating and assaying social media data. former studies have shown that youth are likely to expose suicidal studies and suicidal threat factors online and on social media. For illustration, a study examining exigency room assessment suicidality set up those adolescents were likely to report suicidal creativity not only verbally, but also via electronic means, which included posts on social networking spots, blog posts, instant dispatches, textbook dispatches, and emails. exemplifications similar as drooling on social networks like Twitter, WhatsApp, and Facebook, live blogs, or commentary can be described as novelettish analysis, expressed in these enormous opinions generated by druggies is generallynamed opinion mining.
© 2022, IRJET
|
Impact Factor value: 7.529
2.3 Suicide Risk Assessment Using Machine Learning and Social Network, 2020 In this paper, an increase in anxiety and depression diseases, medicine use, loneliness, domestic violence, and indeed self-murder is anticipated to do in these
|
ISO 9001:2008 Certified Journal
|
Page 1464