AIF-C01 Question 13
Select 2A data scientist is building an AI model to classify emails as spam or not spam. The dataset consists of thousands of email records, each containing the email text and a label indicating whether it is spam or not. Which type(s) of data is/are being used in this scenario?
- A
Labeled data
- B
Unlabeled data
- C
Text data
- D
Time-series data
- E
Structured data
Show answer and explanation
Correct answers: A, C
Explanation
The dataset in this scenario includes labeled data because it contains labels (spam or not spam) for supervised learning. Additionally, the email content is text data because it consists of textual information. The other types of data, such as unlabeled, time-series, and structured, do not apply to the given dataset.
- A. Correct.
Labeled data is correct because the dataset includes labels indicating whether each email is spam or not, which are used for supervised learning.
- B. Incorrect.
Unlabeled data is incorrect because the dataset explicitly has labels, meaning it is not unlabeled.
- C. Correct.
Text data is correct because the content of the emails is textual, which makes it text data.
- D. Incorrect.
Time-series data is incorrect because the emails are not organized in a chronological order for time-dependent analysis.
- E. Incorrect.
Structured data is incorrect because email text is unstructured data, not structured data that fits into a defined schema or table format.