Hope is a cheerful and optimistic state of mind which has its basis in the expectation of positive outcomes. Hope speech reflects the same as they are positive words that can motivate and encourage a person to do better. Non-hope speech reflects the exact opposite. They are meant to ridicule or put down someone and affect the person negatively. The shared Task on Hope Speech Detection for Equality, Diversity, and Inclusion at LT-EDI - RANLP 2023 was created with data sets in English, Spanish, Bulgarian and Hindi. The purpose of this task is to classify human-generated comments on the platform, YouTube, as Hope speech or non-Hope speech. We employed multiple traditional models such as SVM (support vector machine), Random Forest classifier, Naive Bayes and Logistic Regression. Support Vector Machine gave the highest macro average F1 score of 0.49 for the training data set and a macro average F1 score of 0.50 for the test data set.

The advent of social media platforms has revo- lutionized the way we interact, share, learn , ex- press and build our views and ideas. One major challenge of social media is hate speech. Homo- phobia and transphobia encompasses a range of negative attitudes and feelings towards people based on their sexual orientation or gender iden- tity. Homophobia refers to the fear, hatred, or prejudice against homosexuality, while trans- phobia involves discrimination against trans- gender individuals. Natural Language Process- ing can be used to identify homophobic and transphobic texts and help make social media a safer place. In this paper, we explore us- ing Support Vector Machine , Random Forest Classifier and Bert Model for homophobia and transphobia detection. The best model was a combination of LaBSE and SVM that achieved a weighted F1 score of 0.95.