Violence against people on the basis of race, ethnicity, national origin, sexual orientation, gender identity, religious affiliation, age, disability, or serious disease, is still a major issue across many countries. The objective of this course is to deliver a hands-on experience with machine learning algorithms, natural language processing concepts, and network analysis techniques to build effective models on real-world data for the sake of hate speech detection.
What you will learn
This course is intended for those who are interested in developing learning analytics and data science skills for employment in the education, corporate, nonprofit, and military sectors. Experience with programming and statistics will be beneficial to participants.
Module 1: Exploratory Data Analysis
Selecting the right chart for the right job
Bar, Grouped Bar, Stacked Bar, Lollipop charts
Pie, Three-map charts
Line, Area, Stacked Area charts
Histogram, Density, Box-and-Whisker, Swarm charts
Scatter, Correlogram, Heatmap, Hexbin charts
Module 2: Natural language processing
How to use common Text Mining and NLP techniques
How to use NLTK to pre-process text
How to predict the sentiment of any tweet
How to use Regex to clean up Tweets
How to use Scikit-Learn to build a Sentiment Analysis prediction model.
Module 3: Social network analysis
What are networks and what use is it to study them? Concepts: nodes, edges, adjacency matrix, one and two-mode networks, node degree.
Learn concepts such as connected components, giant components, average shortest path, diameter, breadth-first search, preferential attachment.
Network centrality: discuss concepts such as betweenness, closeness, eigenvector centrality (+ PageRank), network centralization.
Community: discuss concepts such as clustering, community structure, modularity, overlapping communities.
Module 4: Web scraping
First, learn the essentials of web scraping, explore the framework of a website and get your local environment ready to take on scraping challenges with Scrapy, BeautifulSoup, and Selenium.
Next, set up a Scrapy crawler and cover the core details that can be applied to building datasets or mining.
Next, cover the basics of BeautifulSoup, utilize the requests library and LXML parser, and scale up to deploy a new scraping algorithm.
Finally, test the model that participants have already built on scraped data.
Duration: 20 hours
Category: Data Science, Machine Learning, Natural Language Processing