The correct answer is converting all text to lowercase and removing punctuation, as these are the two most essential NLP preprocessing steps before tokenization. Lowercasing ensures that words like “Great,” “great,” and “GREAT” are mapped to a single token, preventing the model from treating capitalization variants as distinct features and reducing overall vocabulary size. Removing punctuation is equally critical because tokenizers typically split on whitespace; without this step, punctuation attached to words—such as “great!” or “bad.”—creates noisy tokens like “great!” and “bad.” instead of clean tokens “great” and “bad,” which would dilute the model’s ability to learn meaningful patterns. On the CompTIA AI+ AI0-001 exam, this question tests your understanding of foundational text preparation, often appearing as a multiple-select item where a common trap is choosing stemming or stop-word removal instead. Remember the memory tip: “Clean and case” before you tokenize—strip punctuation and flatten case to keep your tokens pure.
AI0-001 AI Concepts and Foundations Practice Question
This AI0-001 practice question tests your understanding of ai concepts and foundations. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A data scientist is building a natural language processing model to classify customer reviews as positive or negative. Which TWO preprocessing steps are most essential before tokenization? (Select two.)
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Remove punctuation and special characters.
Removing punctuation and special characters (Option B) is essential because tokenizers typically split on whitespace, so punctuation attached to words (e.g., 'great!', 'bad.') would create noisy tokens like 'great!' and 'bad.' instead of clean tokens 'great' and 'bad'. Converting all text to lowercase (Option C) ensures that words like 'Great', 'great', and 'GREAT' are all mapped to the same token, preventing the model from treating them as distinct features and reducing vocabulary size.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Perform stemming or lemmatization.
Why it's wrong here
Stemming is done after tokenization.
✓
Remove punctuation and special characters.
Why this is correct
Removing punctuation helps tokens become clean words.
Related concept
Read the scenario before looking for a memorised answer.
✓
Convert all text to lowercase.
Why this is correct
Lowercasing reduces vocabulary and treats words like 'Good' and 'good' identically.
Related concept
Read the scenario before looking for a memorised answer.
✗
Remove stop words from the text.
Why it's wrong here
Stop word removal is done after tokenization.
✗
Replace missing values with a placeholder.
Why it's wrong here
Missing value handling is not specific to preprocessing before tokenization.
Common exam traps
Common exam trap: answer the scenario, not the keyword
CompTIA often tests the ordering of preprocessing steps, and the trap here is that candidates mistakenly believe stemming, lemmatization, or stop word removal should be done before tokenization, when in fact tokenization must come first to split the text into tokens for those later steps to operate on.
Detailed technical explanation
How to think about this question
Under the hood, tokenizers like those in NLTK or spaCy rely on regular expressions or rule-based splitting; if punctuation is not removed, tokens such as 'hello.' or 'world,' will be treated as distinct from 'hello' and 'world', inflating the vocabulary and reducing the model's ability to generalize. In a real-world scenario, a review containing 'LOVE it!!!' would, after lowercasing and punctuation removal, become 'love it', producing the same tokens as 'love it' from another review, ensuring consistent feature representation across the corpus.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A small business has 20 workstations on the 192.168.1.0/24 network and one public IP from its ISP. The router uses PAT (NAT overload) so all 20 devices share one public address using different source ports. NAT questions test whether you understand the four address terms and which direction each translation applies.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
AI Concepts and Foundations — This question tests AI Concepts and Foundations — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Remove punctuation and special characters. — Removing punctuation and special characters (Option B) is essential because tokenizers typically split on whitespace, so punctuation attached to words (e.g., 'great!', 'bad.') would create noisy tokens like 'great!' and 'bad.' instead of clean tokens 'great' and 'bad'. Converting all text to lowercase (Option C) ensures that words like 'Great', 'great', and 'GREAT' are all mapped to the same token, preventing the model from treating them as distinct features and reducing vocabulary size.
What should I do if I get this AI0-001 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This AI0-001 practice question is part of Courseiva's free CompTIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI0-001 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.