Courses Taught#

Fundamental Laboratories

  • ChEn 285: Fluids Lab

  • ChEn 345: Reaction and Materials Lab

Unit Operation Laboratories

  • ChEn 479

Lecture Courses

Student Comments#

Students have left me over 1600 comments. Student comments are from the end of semester teacher evaluations. The comments range from negative to mixed to positive. I’ve used Google’s generative ai package as given here with the comments on this Kaggle sheet to generate a sentiment (positive, etc.) for each comment. The classification is not perfect as there are some positive comments that are labeled negative and vice versa. The below plot is a representation of the similarity between comments based on embeddings and tSNE reduction. You can mouse over the figure to see the comment at that point. The comments are colored by the sentiment classification.

#import needed packages
import pandas as pd
import plotly.express as px
import plotly.offline as pyo
pyo.init_notebook_mode(connected=True)
from IPython.display import HTML  # Import the HTML function

#import data
df = pd.read_csv('https://raw.githubusercontent.com/clint-bg/clint-bg.github.io/refs/heads/main/activities/support/studentfeedback.csv')

# Create a scatter plot with different colors for each cluster
fig = px.scatter(df, x='tsne_x', y='tsne_y', color='Sentiments', hover_data=['feedback'],
                 title='TSNE Scatter Plot of Student Feedback')

html_string = pyo.plot(fig, include_plotlyjs=True, output_type='div')

display(HTML(html_string))