top of page
A Young Man in the Library

WELCOME TO LIFE EVENT BOOK RECOMMENDER

Get book recommendations based on what you're going through, not what you've done in the past. 

A UC Berkeley MIDS Graduate Capstone Project

About Our Project

We have created a novel categorization methodology to recommend fiction books for young adults ages 13-19 not based on what they’ve done in the past or what others think, but on what they are experiencing in the moment. We are utilizing an ensemble NLP methodology to review book summaries to review, label, and categorize books into different life events and then load them into our application for discovery by our users.

Outdoor Reading

OUR WORK

Technical Overview

Pages of Book

OUR DATA

Our MVP dataset is obtained from the “Best Books Ever Dataset” which was compiled by Lorena Casanova Lozano and Sergio Costa Planells from Goodreads data as part of their Data Science Masters Program. We then cleaned, filtered, and formatted the data. We have 29,652 different books in our dataset with over 14,000 authors and a large expanse of genres.

Open Book

OUR ARCHITECTURE

We cleaned our data in Google Colab. We then loaded our data into an S3 bucket on Amazon Web Services. From there we created EC2 instances with high powered computing resources and launched Jupyter Lab to run our multiple models and evaluation of them. We then moved the results into the S3 bucket and from there link the data to Google Sheets where our application runs.

Holding a Book

OUR MODEL

After analyzing our data, we went with an ensemble model methodology. For some life events, topic modeling was quite adept at understanding the concept. While others were more nuanced and needed a different approach. We used a synsets and lemmas model paired with a fine-tuned BERT model.  We ran both models on the description field of each book to categorize them for search in our application.

Our Application

Our application allows you to search through libraries of books within individual categories in our
"Search Books by Life Event" module.
lifeEventSearch.PNG
SearchCateg.PNG
BookExamp.PNG
Mybooks.PNG

Application Demo

CURRENT RECOMMENDATIONS

Our initial product includes 8 different categorizations of books into different scenarios that our potential users said they would want to read about.

University

Books on attending or being in college/university

Relationships

Books about relationships targeted at dating

Break Ups

Books involving people going through break ups

Weddings

Books involving a wedding 

Family

Books involving familial relationships

Divorce

Books where characters are experiencing divorce

Friends

Books surrounding friendship themes

Death

Books about dealing with the death of others in our lives

Meet the Team

We are three working professionals who at the time of this project were completing our graduate degrees at UC Berkeley MIDS Master of Information and Data Science.

CONTACT US 

For Recommendation Application Access or More Information

Looking at Books
bottom of page