For this task, I collected 40 reviews of McDonald's in English and performed various text processing steps to identify underlying themes.
Steps Taken:
Data Collection:
- Gathered 40 reviews related to McDonald's.
Text Preprocessing:
- Converted text to lowercase.
- Removed punctuation, numbers, and stop words.
- Applied lemmatization to reduce words to their base forms.
Model Building:
- Used the LDA model to identify 5 topics within the reviews.
Visualization:
- Created word clouds to visualize the most frequent terms in each topic.
- Generated a bar chart to show the distribution of topics across the reviews.
Results:
- Word Clouds for Each Topic:
- These word clouds highlight the prominent words in each identified topic, giving a visual representation of the themes present in the reviews.
- Topic Distribution Bar Chart:
- This chart shows the proportion of each topic within the dataset, indicating the prevalence of certain themes in the reviews.
The analysis revealed several key themes, including customer service, food quality, restaurant environment, and specific menu items.
I look forward to hearing your feedback and insights on this analysis. Additionally, I'm eager to see the results of your own topic modeling challenges.
> print(terms)
Topic 1 Topic 2 Topic 3 Topic 4 Topic 5
[1,] "service" "mcdonalds" "food" "long" "breakfast"
[2,] "fry" "lot" "service" "time" "always"
[3,] "bite" "menu" "burger" "love" "restaurant"
[4,] "friendly" "quality" "good" "meal" "excellent"
[5,] "place" "think" "big" "great" "fresh"
[6,] "coffee" "love" "delicious" "staff" "order"
[7,] "option" "especially" "mac" "wait" "good"
[8,] "sandwich" "enjoy" "area" "happy" "enjoy"
[9,] "like" "great" "fantastic" "toy" "choice"
[10,] "cold" "food" "new" "experience" "crowd"