Visualizing comment sentiment

A computing device, comprising:

• a processor;
• and
• a memory including computer readable instructions, which, when executed by the processor, cause the computing device to perform a method for displaying sentiment of a user text comment, the method comprising:
• receiving a text comment;
• providing a vector sequence representing the text comment to a sentiment model configured to output a sequence of sentiment scores for the vector sequence;
• receiving, from the sentiment model, the sequence of sentiment scores for the vector sequence;
• determining cleaned text from the text comment,
• providing the cleaned text to a topic module configured to determine relevance scores between the cleaned text and each topic of a plurality of topics and output the relevance scores;
• receiving, from the topic module, the relevance scores for the cleaned text;
• determining, based on the sequence of sentiment scores for the vector sequence and the relevance scores for the cleaned text, final sentiment scores related to the text comment;
• and
• generating, based on the final sentiment scores, a sentiment visualization for the text comment.

A method for displaying sentiment of a user text comment, comprising:

• receiving a text comment;
• providing a vector sequence representing the text comment to a sentiment model configured to output a sequence of sentiment scores for the vector sequence;
• receiving, from the sentiment model, the sequence of sentiment scores for the vector sequence;
• determining cleaned text from the text comment;
• providing the cleaned text to a topic module configured to determine relevance scores between the cleaned text and each topic of a plurality of topics and output the relevance scores;
• receiving, from the topic module, the relevance scores for the cleaned text;
• determining, based on the sequence of sentiment scores for the vector sequence and the relevance scores for the cleaned text, final sentiment scores related to the text comment, wherein the final sentiment scores indicate a respective sentiment associated with each respective topic of the plurality of topics for each word of a sequence of words in the cleaned text;
• and
• generating, based on the final sentiment scores, a sentiment visualization for the text comment.