Suicide Prediction on Social Media by Implementing Sentiment Analysis along with Machine Learning

Technology is growing day by day and the influence of them on our day-to-day life is reaching new heights in the digitized world. Most of the people are prone to the use of social media and even minute details are getting posted every second. Some even go to the extent of posting even suicide related issues. This paper addresses the issue of suicide and is predicting the suicide issues on social media and their semantic analysis. With the help of Machine Learning techniques and semantic analysis of sentiments the prediction and classification of suicide is done. The model of approach is a four-tier approach, which is very beneficial as it uses the twitter4J data by using weka tool and implementing it on WordNet. The precision and accuracy aspects are verified as the parameters for the performance efficiency of the procedure. We also give a solution for the lack of resources regarding the terminological resources by providing a phase for the generation of records of vocabulary also.

Download Full-text

DETECTION AND CLASSIFICATION OF HATE SPEECH

International Journal of Engineering Applied Sciences and Technology ◽

10.33564/ijeast.2021.v05i11.032 ◽

2021 ◽

Vol 5 (11) ◽

Keyword(s):

Machine Learning ◽

Social Media ◽

Hate Speech ◽

Machine Learning Techniques ◽

The People ◽

Learning Techniques ◽

The Social ◽

Improved Technology

The challenges that are to be faced while handling with hate speech is not a new thing. From thepast few years due to the boosted usage of internet, hateful activities across social media is increasing rapidly. Improved technology has made it possible to create a platform where people can feel free to share their opinions and experiences.it wouldn't be a problem if this is just the case. but we can also see hateful comments running throughout the social media targeting a person or a community. Hate speech is the statement that targets a person or community of people discriminating based on caste, creed, nationality etc. Our project aims at resolving the above problem by using Machine Learning techniques to automatically detect hate speech and classify them into various classes such as extremely positive, positive neutral etc. We have used classifier that works based on the lexicons and finally compare it with other classifiers that doesn't use lexicons. Aimed beneficiaries of this model are the people who are being targeted on social media. Based on the results they can calculate intensity of the comments.

Download Full-text

Feasibility of Adding Twitter Data to Aid Drought Depiction: Case Study in Colorado

10.21203/rs.3.rs-939800/v1 ◽

2021 ◽

Author(s):

Sarbajit Mukherjee ◽

Shih-Yu Wang ◽

Daniella Hirschfeld ◽

Joel Lisonbee ◽

Liping Deng ◽

...

Keyword(s):

Machine Learning ◽

Social Media ◽

Large Population ◽

Crisis Response ◽

Machine Learning Techniques ◽

Drought Severity ◽

Support Vector ◽

Twitter Data ◽

Learning Techniques ◽

Use Of Social Media

Abstract The use of social media, such as Twitter, has changed the information landscape for citizens participation in crisis response and recovery activities. Given that drought progression is slow and also spatially extensive, an interesting set of questions arise: How the usage of Twitter by a large population may change during the development of a major drought alongside how changing usage promotes drought detection? For this reason, by investigating contemporary procedures, this paper scrutinizes the potential to advance drought depiction. Hence, an analysis of how social media data, in conjunction with meteorological records, was conducted towards improvement in the detection of drought and furthermore, its progression. The research utilized machine learning techniques applied over satellite-derived drought conditions in Colorado. Specifically, 3 different machine learning techniques were examined: the generalized linear model, support vector machines and deep learning, each applied to test the integration of Twitter data with meteorological records as a predictor of drought development. It is maintained that the data integration of resources is viable given that the Twitter-based model outperformed the control run which did not include social media input. Furthermore the Twitter-based model was superior in predicting drought severity.

Download Full-text

Crop Yield Prediction Using Machine Learning Techniques

International Journal of Scientific Research in Science Engineering and Technology ◽

10.32628/ijsrset20736 ◽

2020 ◽

pp. 312-315

Author(s):

Ashwini I. Patil ◽

Ramesh A. Medar ◽

Vinod Desai

Keyword(s):

Machine Learning ◽

Crop Yield ◽

Model Performance ◽

High Accuracy ◽

Machine Learning Techniques ◽

Yield Prediction ◽

The People ◽

Learning Techniques ◽

High Production ◽

Day By Day

Today Indian economy depends upon agriculture. More than 70% of the people in India have taken it as a main occupation, day by day for a particular crop; the formers are not getting proper yield as well as profit due to environmental conditions like soil quality, weather, heavy rainfall, drought, seed damages, fertilizers, pesticides. The farmers not able to produce high production, so taking the historical agricultural data records we can predict the crop yield using machine learning techniques like Linear regression, comparative analysis are done with decision tree, KNN algorithms, using these to achieve the high accuracy and model performance is computed.

Download Full-text

Fake News Detection on Social Media using Machine Learning Techniques

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.g5428.059720 ◽

2020 ◽

Vol 9 (7) ◽

pp. 940-943

Keyword(s):

Machine Learning ◽

Social Media ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Fake News ◽

Huge Number ◽

Web Based ◽

Distributed Information ◽

Learning Techniques ◽

Day By Day

: Web based life administrations, as Facebook and Twitter, Renren, Instagram, and linkedin have recently become an enormous and persistent supply of day by day news. These stages give a huge number of clients and give numerous administrations, for example, content arrangement and distributing. Not all distributed information via internet based medium is dependable and exact. Numerous individuals attempt to distribute fake and mistaken news so as to control general conclusion. Counterfeit news might be intentionally made to advance money related, political and public premiums, and can lead to unsafe effects on people convictions and choices.. In this paper we examine different systems for recognizing counterfeit information via internet based networking medium. Our point is to locate a dependable and right model that arranges a given article as fake or genuine. For identification of fake articles we use machine learning algorithms.

Download Full-text

A Brief Survey on Text Classification Using Various Machine Learning Techniques

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse.v8i1.521 ◽

2018 ◽

Vol 8 (1) ◽

pp. 14

Author(s):

Padmavathi .S ◽

M. Chidambaram

Keyword(s):

Machine Learning ◽

Text Classification ◽

Fixed Number ◽

Machine Learning Techniques ◽

Online Information ◽

Rule Based ◽

Learning Techniques ◽

Machine Learning Approach ◽

Rule Based Approach

Text classification has grown into more significant in managing and organizing the text data due to tremendous growth of online information. It does classification of documents in to fixed number of predefined categories. Rule based approach and Machine learning approach are the two ways of text classification. In rule based approach, classification of documents is done based on manually defined rules. In Machine learning based approach, classification rules or classifier are defined automatically using example documents. It has higher recall and quick process. This paper shows an investigation on text classification utilizing different machine learning techniques.

Download Full-text