Skip to content

Implementations and Experiments of various ML models.

Notifications You must be signed in to change notification settings

haru-256/ml-sandbox

Repository files navigation

ML-Sandbox

This repository provides implementations and experiments of various ML models.

Directory Structure

.
├── sentiment__analysis/ # Sentiment Analysis
├── sequential_recommendation/ # Sequential Recommendation
└── two_tower_recommendation/ # Sequential Recommendation

Problem Types

This repository deals with the following problem types:

  1. Sequential Recommendation
  2. Two-Tower Recommendation
  3. Sentiment Analysis

Sequential Recommendation

According to https://paperswithcode.com/task/sequential-recommendation, Sequential Recommendation is the following.

Sequential recommendation is a sophisticated approach to providing personalized suggestions by analyzing users' historical interactions in a sequential manner. Unlike traditional recommendation systems, which consider items in isolation, sequential recommendation takes into account the temporal order of user actions. This method is particularly valuable in domains where the sequence of events matters, such as streaming services, e-commerce platforms, and social media.

This repository has the following models.

For more information on Sequential Recommendation, please refer to the sequential_recommendation directory.

Two-Tower Recommendation

Sentiment Analysis

According to https://en.wikipedia.org/wiki/Sentiment_analysis, Sentiment Analysis is the following.

Sentiment analysis (also known as opinion mining or emotion AI) is 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. With the rise of deep language models, such as RoBERTa, also more difficult data domains can be analyzed, e.g., news texts where authors typically express their opinion/sentiment less explicitly.[1]

This repository has the following models.

For more information on Sentiment Analysis, please refer to the sentiment_analysis directory.

About

Implementations and Experiments of various ML models.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published