![• CF[Collaborative Filtering] is a recommender systems
technique that helps people discover items that are most
relevant to them. At Facebook, this might include pages,
groups, events, games, and more. CF is based on the idea that
the best recommendations come from people who have similar
tastes. In other words, it uses historical item ratings of like-
minded people to predict how someone would rate an item.](https://image.slidesharecdn.com/machinelearninginonfacebook-180408155120/85/Machine-learning-in-on-facebook-6-320.jpg)
![Bayes' Theorem
p(Ck)= p (occurrence of class) [prior]
p(x)= p (instance of word) [likelihood]](https://image.slidesharecdn.com/machinelearninginonfacebook-180408155120/85/Machine-learning-in-on-facebook-11-320.jpg)
Machine learning in & on facebook
- 1. machine learning in & on facebook Sai Srinivas 15311A0568
- 2. In Facebook • Automatic friend tagging suggestions: When a pic is uploaded on facebook, a suggestion asking if you want to tag your friend in the pic appears. This is done by Facebook's face detection and recognition algorithms based on the advanced deep learning neural network research project Deepface. • Mutual friend analysis: Facebook uses the clustering algorithm to find mutual friends. • Newsfeed: facebook uses ML to arrange your Newsfeed too. Like posts of close friends may come up first. Posts related to your favourite pages come up first. • Friend Suggestions: Machine learning is used by FB to suggest new friends based on mutual friend circles.
- 6. • CF[Collaborative Filtering] is a recommender systems technique that helps people discover items that are most relevant to them. At Facebook, this might include pages, groups, events, games, and more. CF is based on the idea that the best recommendations come from people who have similar tastes. In other words, it uses historical item ratings of like- minded people to predict how someone would rate an item.
- 8. Ads on facebook • The process of placing an ad on News Feed is a complicated dance. Facebook has to decide not only which ad to show to its users, but when to show it to them. There isn't a dedicated "slot," so to speak, for an ad in News Feed, so the team must time the ads based what the user is doing on Facebook at that given moment.
- 9. On Facebook Business people use facebook data to: * Promote relevant products * Grow brand awareness * Get qualified leads * Close the loop
- 10. Sentiment Analysis • Sentiment Analysis can be used to automatically detect emotions, speculations, evaluations and opinions in the content that people write. The sentiment analysis tool extracts data from the comments on a post, cleanses the data and processes it to give us an analysis in the form of a graph that classifies all the comments into polarity and sentiments. This provides insight into comments by classifying them into three polarities (positive, negative & neutral) and into six different emotions (anger, disgust, fear, joy, sadness, surprise). Most of the algorithms for sentiment analysis are based on a classifier
- 11. Bayes' Theorem p(Ck)= p (occurrence of class) [prior] p(x)= p (instance of word) [likelihood]
- 12. • Its classifications regarding the decisions are surprisingly accurate. The above function returns an object of class (data.frame) with seven columns (anger, disgust, fear, joy, sadness, surprise and best_fit category). This best_fit is the most likely sentiment category among the six emotionsfor a given content item. Similarly, we will classify polarity in the text and combine the emotions of all the comments. In simple words the approach is, if a piece of content has more positive keywords than negative keywords, it’s a positive content; if it has more negative keywords than positive keywords, it’s a negative content.
- 13. • After the classification, we fetch the “best_fit” category for analysis. When all the data is cleansed and processed we enter the next phase: strategic representation of data. In this phase the processed data is subjected to a function named ‘ggplot()’, which plots the distribution of emotions (anger, disgust, fear, joy, sadness, surprise). Similarly, we can plot the distribution of polarity (positive, negative and neutral).
- 15. Deep Facebook Analysis for business *Analyze Your Competitors *Gather Your Data *Analyze Your Facebook Page Data *Analyze Your Facebook Posts *Ask Yourself the Right Questions *What to Do After Checking Page & Post Data
- 23. Conclusion • Facebook use our data to provide better services to us and business people use this platform to manufacture the products based on people's interest which is a good sign.