A media streaming service wants each viewer comment labeled positive, negative, or mixed toward a show. The team does not need actor names or city names pulled out of the comment. Which task fits?
Select an answer to reveal the explanation.
Short Explanation
Attitude is the tone of the note, not the signature at the bottom. Sentiment classification tells you whether the comment is positive, negative, or mixed. The trap is pulling out names when the service asked for the tone.
Full Explanation
Sentiment classification assigns an attitude label to text. For these viewer comments the labels are positive, negative, or mixed toward a show, which is a judgment about the writer's stance rather than a list of who or where is mentioned. The streaming team said actor names and city names are not required, so the task stops at attitude. Named-entity recognition finds spans such as people and places and would extract the mentions the team does not need, without scoring tone. Edit distance counts the cheapest character edits between two strings and has no attitude label at all. Stop-word removal drops common function words as a cleaning step and does not decide whether a comment is positive, negative, or mixed. Exam caveat: a comment can name a show and still be any attitude, so the presence of an entity is not a sentiment label. Operational check: read a sample of labeled comments and confirm the label matches the praise or complaint, not merely whether an actor or a city was mentioned.