Automated Essay Grader App with NLP

Drace Zhan
Jake Bialer
and
Posted on Apr 8, 2017

In 2016, it was estimated that over four million standardized exams were administered with an essay section.

testtakers

  • The most popular standardized exam of 2016, the ACT, requires two additional weeks of processing time in order to return essay scores
  • Typically an essay requires two scorers. Assuming each essay takes only one minute to score, it would take 135000 man hours to score four million essays.
  • Automating part of the process makes it possible to eliminate one of the human scorers while retaining the other to act as control.  That can save the industry an estimate of two million dollars per year.

 

The method of automating the essay requires several steps.  First, training samples are required for each individual topic.  This can be accomplished by having the "control" scorer act as the first reader and assign a score to each essay in a database.  The model discussed in this blog required only a sample of thirteen thousand essays to effectively grade eight various topics from different student age groups.  Features are extracted by examining the proportion of stopwords used within the essay, vectoring the essay and topic modeling.

Visualization of the topics within the essay can be extracted and displayed to students and educators for better clarity with tools such as pyLDAVis (a Python module).

pylab

 

These are then transferred to gradient boosted trees and convolutional neural networks to produce a predicted score as well as predictions of probabilities for each grade assignment (a useful additional feature to examine if an essay merits a higher or lower grade due to other influences).

Visual process

Visual process

 

Various models have been tested but due to the current sample size of this particular training set (only thirteen thousand essays), the power of the neural network could not be properly harnessed.  As a result, the best performing model, which is employed for the app's current prediction scores, were able to predict with a cross validated accuracy score of 94% with minimal log loss.  The essay predictor was always able to predict within one point of the "control" essay score in 100% of the cases.  Since typical industry standards, disagreement between manual essay grading leads to point differences so this can model such variations.  In addition, with a larger sample size, the convolution neural network can be called upon as it "learns" previous behaviors and can eventually train itself on essay format changes without the need to be fed training samples from more essays.

A demonstration of the app can be found here with an example of the current prototype model grading and assessing one essay.

Note that private information such as personal names within the essay is censored with @CAPS.

Note that private information such as personal names within the essay is censored with @CAPS.

 

In the future, additional features can be added towards the essay such as improvement tips on writing, personalized tuning for educators on weights of the essay and so forth. There are also some short comings due to the sample size used to train the app. For example, when the user is using language that is far more sophisticated (Ms or PhD level) than the student population the app used to train upon, the vocabulary is often not recognize by the model and the app would thus grade the essay poorly due to a perceived "off-topic" notion. This can be combated in the future by training on a much larger corpus size than the model currently had access to.

About Authors

Drace Zhan

Drace Zhan

Drace Zhan has honed the bulk of his communication skills by teaching math and reading skills to high school and college graduates since 2007. A whiz at translating abstruse concepts to easily understood terms, he entered the field...
View all posts by Drace Zhan >
Jake Bialer

Jake Bialer

During the past eight years, I’ve worked as a full-stack developer, data analyst, and journalist. I’ve a track record of finding unique datasets through web scraping and using them to help companies solve key business problems. My NYCDSA...
View all posts by Jake Bialer >

Related Articles

Leave a Comment

No comments found.

View Posts by Categories


Our Recent Popular Posts


View Posts by Tags

#python #trainwithnycdsa 2019 airbnb Alex Baransky alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus API Application artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep Bundles California Cancer Research capstone Career Career Day citibike clustering Coding Course Demo Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day Discount dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Hiring Partners Industry Experts Instructor Blog Instructor Interview Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research Meet the team meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Online Online Bootcamp Open Data painter pandas Part-time Portfolio Development prediction Prework Programming PwC python python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau team TensorFlow Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping Weekend Course What to expect word cloud word2vec XGBoost yelp