Inspiration:
1.Public opinion plays an important role on individual's opinion and twitter providing the forum for expressing their opinion which can be offensive sometimes.
- These offensive tweets and opinions may adversely affect someone's life . So it's important to know its effects by classifying these sentiments.
What it does
It classifies the sentiments in a positive, negative or neutral manner to analyse the trend of how it affects an individual's life.
How we built it
1.By building a machine learning model which performs EDA (Exploratory data analysis) and then pre processes multiple datasets to train a model which is used to predict the sentiments behind the tweets. 2.This model mainly focuses on these algorithms: a.Logistic regression b.Support vector Machine c . Knn d. xg boost
Challenges we ran into
The biggest challenge which approaching this problem was to fetch the real time tweets from tweeter i.e. datasets of tweets as tweeter imposes some security and privacy policies which is accessible only through API's.
Accomplishments that we're proud of
We are proud of that we were able to address a real time problem by providing a solution which can help people by getting them acknowledged with the sentiments and the trends where these sentiments lead to.
What we learned
We learned applying multiple classification algorithms and its approach over a dataset.
What's next for Twitter's Tweet Analysis
Tweet analysis can be also used for social marketing as it provides customer's feedback and related information.
Built With
- matplotlib
- numpy
- pandas
- python
- scikit-learn
- seaborn
- sklearn
Log in or sign up for Devpost to join the conversation.