Sentiment Analysis.
In this project, I created a web application using Streamlit and Heroku app websites. I have used the spacy toolbox for text manipulation. For feature engineering, TFIDF is used. Linear Support vector machine algorithm is used to build up the pipeline.
For more on what is sentimental analysis here is Wikipedia description.
"Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine." (https://en.wikipedia.org/wiki/Sentiment_analysis)
Go to Project
Spam Finder.
In this project, I created a web application using Streamlit and Heroku app websites. I have used the spacy toolbox for text manipulation. For feature engineering, TFIDF is used. Linear Random Forest Classifier algorithm is used to build up the pipeline.
For more on what is anti-spam techniques here is Wikipedia description.
https://en.wikipedia.org/wiki/Email_filtering
"Various anti-spam techniques are used to prevent email spam (unsolicited bulk email).
No technique is a complete solution to the spam problem, and each has trade-offs between incorrectly rejecting legitimate email (false positives) as opposed to not rejecting all spam (false negatives) – and the associated costs in time, effort, and cost of wrongfully obstructing good mail.
Anti-spam techniques can be broken into four broad categories: those that require actions by individuals, those that can be automated by email administrators, those that can be automated by email senders and those employed by researchers and law enforcement officials."
Go to Project
Yelp Project API.
In this project, I created a web application using Javascript. Please visit the project.
After you record your voice, it will convert it to text. Textblob toolbox is then used for text classification. And yelp API and IP API are used to offer you restaurants you should visit next time.
Go to Project
YouCook Project.
In this project I developed a web app (YouCOOK) that searches and extracts ingredients of YouTube how-to-cook videos by applying Natural Language Processing using video captions so that users can scan videos by identified ingredients. I have trained a custom Named Entity Recognition model with spaCy toolbox and deployed to AWS by Flask framework.
Go to Project
Go to Presentation
QA Analyzer Project.
In this project, I have used Bert transformer for natural language processing for the question and answering website using Streamlit and Heroku deployment. Users copy and paste their text and write a question related to a given text. The model evaluates and answers the question.
Go to Project
Disaster Classification.
In this project, I have used tweeter text to classify if the text is related to a disaster or not. I have tried automatic machine learnerg, Word2Vector embedding using Convulational Neural Networks and lastly used Bert for this classification problem.
Go to Project
Disease Finder.
In this project, I created a clinical named entity recognition model that can recognize the disease names from clinical text. This project is similar in terms of my youcook project. I have used the SpaCy toolbox and trained the NER model. On the website you can copy and paste your text and the model will find the disease for you.
Go to Project
