π₯ Sentiment Rating Prompts
Abstract
This section covers the prompts for "Sentiment Rating" task.
Sentiment Rating is a task in natural language processing which involves assigning a score (for example, in the range of 0 to 5) for the given text. Depending on the sentiment expressed in the text, the score is assigned.
For example, the text expressing (i) positive sentiment gets a score close to 5 and (ii) negative sentiment gets a score close to 0. For example, a score of 4.1 represents positive sentiment and a score of 1.2 represents negative sentiment. For this task, you can write a prompt like this
Prompt
You are an expert English linguist. Give a sentiment rating in the range of 0 to 5 to the given tweet.
High rating represents positive sentiment, low resource represents negative sentiment and moderate scores
represent neutral sentiment.
Tweet: βοΈ **Starting the day off with a grateful heart and a positive mind. Today is going to be a great
day!** #positivevibes #newbeginnings #mindsetmatters
Constraints: First generate the rating with the delimiter βSentiment Ratingβ and then generate the explanation
with the delimiter βExplanationβ.
Sentiment Rating:
Sentiment Rating: 5
Explanation: The tweet uses several positive words and phrases, such as "grateful heart," "positive mind,"
"great day," "positive vibes," "new beginnings," and "mindset matters." The use of the sun emoji also
suggests a positive mood. Overall, the tweet conveys a strong sense of optimism and hope for the future.