SirinTales

Inspiration💡❤️

people deal with this cauldron of feelings - of fear, guilt, shame, anger, trauma, depression, apathy etc... Every feeling is legitimate and those who have experienced sexual assault have a variety of ways of dealing with it. But often, at least in India, there is no outlet for these feelings. People bottle it up and keep them in a cupboard neatly locked up, hoping never to open it again.

SIRINTALES is our attempt to help people feel better through sharing.

What it does👨🛠📋

People all over, can post your experiences about dealing with sexual assault, sexism and bystander intervention. Automatic classification of the type of sexual harassment will enable people who want to make a change in society to better analyze the data.

How we built it👨‍💻

Data has been collected from Safecity, which collects anonymous reports of crimes in public spaces. The top three most dense categories groping/touching, staring/ogling, and commenting, to use as our dataset. We would be using the below evaluation metrics for:- Binary Classification:- Accuracy we used html, css ,bootstrap for the website We have used the below machine learning models for single-label classification Logistic Regression (as a baseline model)

Challenges we ran into💦

we did this project in 10 hrs . It was difficult to find data initially and choose right algorithms to classify data and make model more accurate.

Accomplishments that we're proud of🏆

we are proud that we are going to help many women to smile and to let them share their stories over the globe. Aggregation of data would also be made possible through classification which could prove to be an important use case in enabling faster actions by the authorities. As we already have many personal stories about sexual abuse shared online through this case study we would make scientific use of the data.

What we learned📚

we learnt the use of sklearn library and use of many different algorithms , and EDA

What's next for Untitled➡️

we plan to integrate ml model into the site and use more data to make model more accurate. In time and with enough stories, we hope to affect policy changes in India.