Classifying and Searching News Articles from Key Phrases: ML Experience

Who?

This story consists of the users of Huffington Post, the data scientists developing the AI and the AI.

How much does the data scientist understand the story and data?

The data can be used for supervised learning. Also, the data is valid based because these are just news article. One thing we are not sure is who the readers are.

What models and analysis did the data scientist and AI apply to fulfill the need of the people or the community?

Natural Language Processing (NLP), Logistic Regression and Twin Neural Network

Can the data scientist estimate and select data for their goals from the story? Can they map data sets from data selection onto appropriate ML models?

Yes, the data can be modeled to be key word extraction, classification and searching.

What in-depth knowledge and experience with ML algorithms and ML stories does the data scientist need?

We can use NLP and various types regression models and neural networks.

Over what time period was the data collected? How much time did it take to develop effective models? How efficient is the modeling/algorithm?

Data was collected over 6 years. 20K samples were processed over two days for keyword extraction. The Classification of the dataset can be done within 5 mins. o The search should occur happen under a second.

Can the data scientist determine the acceptance level of the model (validation with accuracy and runtime performance) considering the targeted users?

For classification, the dataset provides classifications that are provided with the articles so validation and accuracy can be determined from those and classification of an article should be under 5 minutes. For keyword extraction, we do not know what the keywords should be so we cannot estimate accuracy and the time of execution can take 10 minutes to process an article. For search results, the search should occur in under a second and the results to return all related articles with the highest score of manually ranked articles giving the highest possible normalized cumulative discounted gain

Which parts of the process involved machine and deep learning?

Deep learning occurred in the searching and classification used machine learning.

Explain the ML model you are using?

We are using NLP for key word extraction, Logistic regression, Random Forrest, Naive Bayes, or a neural network for classification and a neural network for searching

Welcome Back!

Login to your account below

Create New Account!

Fill the forms bellow to register

Retrieve your password

Please enter your username or email address to reset your password.