Assignment 1: Exploring AI Fundamentals and Tools
⚠️To maximize your points and fully benefit from this assignment, please take the time to read all the directions thoroughly. The goal is to ensure that the assignment is engaging and equips you with practical skills that you can apply in your everyday life. ✅
Introduction
Have you ever wondered how companies use Artificial Intelligence (AI) to understand customer opinions or enhance their products? AI tools can analyze vast amounts of data in seconds, helping businesses make informed decisions. In this assignment, you will learn about sentiment analysis, a technique that helps gauge customer feelings through text data. You will explore AI tools like Claude (a Generative AI), OpenAI (ChatGPT, a Conversational AI), and Google Colab (a Cloud-Based Development Environment). By analyzing the outputs from these tools, you will gain insights into how AI can be applied to real-world business scenarios.
Objective
This assignment will teach you how to use AI tools to analyze customer feedback and understand their sentiment. You will learn about polarity and subjectivity, two key metrics essential for interpreting customer opinions. The outputs from Claude will reveal the benefits of AI in business contexts, while OpenAI will provide insights into the risks associated with AI technologies. By the end of this assignment, you will be able to articulate how these insights can be applied in practical settings to enhance decision-making and strategy in business.
Step-by-Step Instructions
Step 1: Create Accounts on AI Platforms
Follow these simple steps to create accounts:
1. Claude (Generative AI):
Visit https://claude.ai.
Click “Sign Up” and follow the instructions (no credit card required).
2. OpenAI (ChatGPT – Conversational AI):
Visit https://www.openai.com/chatgpt.
Click “Sign Up” and follow the instructions.
3. Google Colab (Cloud-Based Development Environment):
Create a new notebook by visiting https://colab.research.google.com.
Click on “New Notebook” at the bottom right.
Step 2: Familiarize Yourself with AI Types
Read about the following key types of AI:
Narrow AI: AI designed for a specific task, like a recommendation system on Netflix.
General AI: A theoretical form of AI that can perform any intellectual task that a human can do.
Superintelligent AI: AI that surpasses human intelligence (not yet created).
Generative AI: AI that can create new content, such as art or music (e.g., Claude).
Conversational AI: AI that engages in dialogue with users (e.g., OpenAI’s ChatGPT).
Descriptive AI: AI that summarizes or analyzes past events.
Predictive AI: AI that forecasts future outcomes based on past data.
Prescriptive AI: AI that offers recommendations for actions to take.
Reactive AI: AI that responds to specific inputs but does not learn from experiences.
Step 3: Conduct AI Tests and Document Findings
1. Claude (Generative AI): Use the following prompt to explore AI benefits:
Prompt to Copy: “What are the benefits of AI in business? Please give some examples of narrow AI in everyday use.”
Directions: Paste the prompt into Claude and document the response. Reflect on how these benefits can be applied in various industries. In your paper, include specific examples from Claude’s output to illustrate the advantages of using AI in business contexts.
Feel free to experiment!
2. OpenAI ChatGPT (Conversational AI): Use the following prompt to learn about AI types:
Prompt to Copy: “Explain the difference between generative AI and predictive AI, and discuss potential risks of using AI in business.”
Directions: Paste the prompt into ChatGPT and document the response. Consider how these risks might affect businesses and consumers. Be sure to incorporate relevant points from ChatGPT’s output in your paper to discuss the implications of these risks on business strategies.
Feel free to experiment!
3. Google Colab (Cloud-Based Development Environment): Create a new notebook and use the following code for sentiment analysis:
# Install TextBlob if not already installed
!pip install textblob
from textblob import TextBlob
reviews = [
“I love this product! It works wonderfully.”,
“The product is okay, not great but not bad.”,
“I had a terrible experience with customer service.”,
“This is the best purchase I’ve ever made!”,
“I am not satisfied with the quality.”
]
for review in reviews:
blob = TextBlob(review)
print(f”Review: {review}nSentiment: {blob.sentiment}n”)
To Run the Code in Google Colab and Get the Output, Follow These Steps:
Open Google Colab: Go to Google Colab.
Create a New Notebook:
Click on “File” in the top left corner.
Select “New Notebook” from the dropdown menu.
Insert Code into a Cell:
You will see a cell (a box) where you can write code.
Copy the provided code for sentiment analysis above.
Paste the Code: Click inside the cell and paste the copied code.
Run the Code: You can run the code by clicking the “Run” button (a play icon) on the left side of the cell. Alternatively, you can press Shift + Enter on your keyboard.
View the Output: After running the cell, the output will appear directly below the cell. It will show the sentiment analysis results, which include polarity and subjectivity.
Understanding Sentiment Analysis Scores
Before interpreting the results, it is essential to understand what the polarity and subjectivity scores mean:
Polarity:
Ranges from -1.0 to 1.0:
-1: Strongly negative sentiment (e.g., “I hate this product.”)
0: Neutral sentiment (e.g., “The product is okay.”)
1: Strongly positive sentiment (e.g., “I love this product!”)
Subjectivity:
Ranges from 0.0 to 1.0:
0.0: Very objective (e.g., factual statements)
0.5: Neutral, somewhat opinionated (e.g., personal opinions without strong emotion)
1.0: Very subjective (e.g., highly opinionated statements)
Example Output
The output from the sentiment analysis will look something like this:
Review: I love this product! It works wonderfully. Sentiment: Sentiment (polarity=0.8, subjectivity=0.9)
Review: The product is okay, not great but not bad. Sentiment: Sentiment (polarity=0.0, subjectivity=0.5)
Review: I had a terrible experience with customer service. Sentiment: Sentiment (polarity=-0.7, subjectivity=0.9)
Review: This is the best purchase I’ve ever made! Sentiment: Sentiment (polarity=1.0, subjectivity=1.0)
Review: I am not satisfied with the quality. Sentiment: Sentiment (polarity=-0.5, subjectivity=0.6)
Using the Example Output:
The above output serves as an example for you to interpret the sentiment analysis results. Here is how to interpret each output:
Interpretation of Example Output:
Review: I love this product! It works wonderfully. Sentiment: Sentiment(polarity=0.8, subjectivity=0.9) Interpretation: The polarity score of 0.8 indicates a strong positive sentiment, while the subjectivity score of 0.9 indicates that this review is highly opinion-based, reflecting a personal and enthusiastic viewpoint.
Review: The product is okay, not great but not bad. Sentiment: Sentiment(polarity=0.0, subjectivity=0.5) Interpretation: A polarity score of 0.0 suggests a neutral sentiment, while a subjectivity score of 0.5 indicates a balanced opinion, neither strongly positive nor negative.
Review: I had a terrible experience with customer service. Sentiment: Sentiment(polarity=-0.7, subjectivity=0.9) Interpretation: The polarity score of -0.7 indicates a strong negative sentiment, and a subjectivity score of 0.9 shows that the review is based on personal experience and feelings.
Review: This is the best purchase I’ve ever made! Sentiment: Sentiment(polarity=1.0, subjectivity=1.0) Interpretation: A polarity score of 1.0 represents extreme positivity, and the subjectivity score of 1.0 indicates a highly personal opinion.
Review: I am not satisfied with the quality. Sentiment: Sentiment(polarity=-0.5, subjectivity=0.6) Interpretation: The polarity score of -0.5 shows dissatisfaction, while the subjectivity score indicates that this is based on personal experience.
You have been given an example to guide you. Now, it is your turn to create your own interpretations for this assignment. Please complete the Real-World Example section as part of your work.
Real-World Example: Customer Feedback Analysis
As a business owner looking to assess customer satisfaction for a new product, analyzing customer feedback can be incredibly valuable. You can leverage the following customer reviews to gain insights into overall sentiment. To facilitate your analysis, use the provided code in Google Colab. Simply copy and paste the code, run it, and you will receive sentiment outputs that can guide your understanding of customer perceptions.
!pip install textblob
from textblob import TextBlob
feedback = [
“The new smartphone is amazing and user-friendly!”,
“I love the camera quality but the battery life is disappointing.”,
“Terrible experience! The phone crashed after a week.”,
“Great value for money, highly recommend!”,
“The software updates are too frequent and annoying.”
]
for response in feedback:
blob = TextBlob(response)
print(f”Feedback: {response}nSentiment: {blob.sentiment}n”)
Expected Output:
The output from the above code will look similar to this:
Feedback: The new smartphone is amazing and user-friendly! Sentiment: Sentiment (polarity=0.9, subjectivity=0.9)
Feedback: I love the camera quality but the battery life is disappointing. Sentiment: Sentiment (polarity=0.3, subjectivity=0.7)
Feedback: Terrible experience! The phone crashed after a week. Sentiment: Sentiment (polarity=-0.8, subjectivity=1.0)
Feedback: Great value for money, highly recommend! Sentiment: Sentiment (polarity=0.8, subjectivity=0.9)
Feedback: The software updates are too frequent and annoying. Sentiment: Sentiment (polarity=-0.4, subjectivity=0.8)
Interpretation of Your Results:
To enhance the feedback analysis, it is essential to interpret the sentiment analysis results with a focus on polarity and subjectivity. Use the first example as a framework to guide your interpretations, ensuring that you not only analyze the output but also discuss how these insights can be harnessed to create competitive advantages. This approach will provide valuable context and actionable recommendations for improvement.
Feedback: The new smartphone is amazing and user-friendly! Sentiment: Sentiment (polarity=0.9, subjectivity=0.9) Interpretation: Explain.
Feedback: I love the camera quality, but the battery life is disappointing. Sentiment: Sentiment (polarity=0.3, subjectivity=0.7) Interpretation: Explain.
Feedback: Terrible experience! The phone crashed after a week. Sentiment: Sentiment (polarity=-0.8, subjectivity=1.0) Interpretation: Explain.
Feedback: Great value for money, highly recommend! Sentiment: Sentiment (polarity=0.8, subjectivity=0.9) Interpretation: Explain.
Feedback: The software updates are too frequent and annoying. Sentiment: Sentiment (polarity=-0.4, subjectivity=0.8) Interpretation: Explain.
When drafting your paper, incorporate your interpretations and explain how they can contribute to your business’s growth and provide a competitive advantage. Use the example output as a reference for structure and clarity. Additionally, think of another instance where you could leverage this tool to benefit your current or future business. Be sure to include specific examples and details to enrich your assignment. As always, feel free to experiment with these tools!
**Deliverables**
APA 7 Formatted Paper: Submit a paper of 3-6 pages (not including the cover page or references), including:
Title Page
Introduction
Main Types of AI
Hands-On AI Testing
Analysis and Recommendations
Conclusion
References
Additional Notes for Each Section:
Title Page: Include the title of your assignment, your name, course, and date.
Introduction: Summarize the importance of AI in business and introduce sentiment analysis, mentioning the outputs you expect from Claude and OpenAI.
Main Types of AI: Describe the various types of AI and provide real-world examples for each type, including Claude, OpenAI, and Google Colab.
Hands-On AI Testing: Discuss your interactions with Claude and ChatGPT, including the prompts you used and the responses you received. Explain how these tools helped you understand AI applications and their real-world relevance.
Analysis and Recommendations: Present your findings from the sentiment analysis, highlighting key insights and their implications for businesses. Discuss how the outputs can inform decision-making in areas such as product development and customer engagement.
Conclusion: Reflect on the overall learning experience, emphasizing the practical applications of AI in business decision-making and strategy.
References: List all sources cited in your paper in APA 7 format. Make sure you use in-text citations to substantiate your thoughts and show your sources of information. Papers without in-text citations or references will be returned for revision (see example below).
APA 7 In-Text Citation and References Requirements