Sentiment-based classification of media content
A set of comments associated with an item of media content is identified. A set of sentiment scores associated with the set of comments is generated, wherein each sentiment score indicates a type of sentiment expressed in a comment. The sentiment profile is generated responsive at least in part to the set of sentiment scores, the sentiment profile indicating the types of sentiment expressed in comments associated with the item of media content and stored in association with the item of media content.
1. A computer-implemented method, comprising:
identifying, at a server, a plurality of comments associated with a content item;
generating, for each of the plurality of comments, a plurality of sentiment scores each associated with a sentiment from a plurality of sentiments by applying a sentiment classifier for each sentiment of the plurality of sentiments, wherein a sentiment score for a sentiment is generated using the sentiment classifier and wherein a value of the sentiment score for the sentiment indicates a likelihood of a corresponding comment being associated with the sentiment;
storing, for each comment of the plurality of comments, the plurality of sentiment scores;
receiving, from a user device, a request to present information associated with the plurality of sentiment scores associated with the plurality of comments; and
in response to receiving the request, causing a subset of the plurality of sentiment scores associated with a corresponding subset of the plurality of comments to be presented by the user device.
2. The computer-implemented method of claim 1 , wherein each sentiment score of the plurality of sentiment scores is a continuous value.
3. The computer-implemented method of claim 1 , wherein the request is a request that indicates a sentiment from the plurality of sentiments.
4. The computer-implemented method of claim 1 , wherein the plurality of comments includes at least one thread of comments, wherein the thread of comments includes a parent comment and at least one reply to the parent comment.
5. The computer-implemented method of claim 1 , wherein each comment in the plurality of comments is associated with a value that indicates a number of users that agree with the comment.
6. A computer-implemented system, comprising:
a hardware processor that:
identifies, at a server, a plurality of comments associated with a content item;
generates, for each of the plurality of comments, a plurality of sentiment scores each associated with a sentiment from a plurality of sentiments by applying a sentiment classifier for each sentiment of the plurality of sentiments, wherein a sentiment score for a sentiment is generated using the sentiment classifier and wherein a value of the sentiment score for the sentiment indicates a likelihood of a corresponding comment being associated with the sentiment;
stores, for each comment of the plurality of comments, the plurality of sentiment scores;
receives, from a user device, a request to present information associated with the plurality of sentiment scores associated with the plurality of comments; and
in response to receiving the request, causes a subset of the plurality of sentiment scores associated with a corresponding subset of the plurality of comments to be presented by the user device.
7. The computer-implemented system of claim 6 , wherein each sentiment score of the plurality of sentiment scores is a continuous value.
8. The computer-implemented system of claim 6 , wherein the request is a request that indicates a sentiment from the plurality of sentiments.
9. The computer-implemented system of claim 6 , wherein the plurality of comments includes at least one thread of comments, wherein the thread of comments includes a parent comment and at least one reply to the parent comment.
10. The computer-implemented system of claim 6 , wherein each comment in the plurality of comments is associated with a value that indicates a number of users that agree with the comment.
11. A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method, the method comprising:
identifying, at a server, a plurality of comments associated with a content item;
generating, for each of the plurality of comments, a plurality of sentiment scores each associated with a sentiment from a plurality of sentiments by applying a sentiment classifier for each sentiment of the plurality of sentiments, wherein a sentiment score for a sentiment is generated using the sentiment classifier and wherein a value of the sentiment score for the sentiment indicates a likelihood of a corresponding comment being associated with the sentiment;
storing, for each comment of the plurality of comments, the plurality of sentiment scores;
receiving, from a user device, a request to present information associated with the plurality of sentiment scores associated with the plurality of comments; and
in response to receiving the request, causing a subset of the plurality of sentiment scores associated with a corresponding subset of the plurality of comments to be presented by the user device.
12. The non-transitory computer-readable medium of claim 11 , wherein each sentiment score of the plurality of sentiment scores is a continuous value.
13. The non-transitory computer-readable medium of claim 11 , wherein the request is a request that indicates a sentiment from the plurality of sentiments.
14. The non-transitory computer-readable medium of claim 11 , wherein the plurality of comments includes at least one thread of comments, wherein the thread of comments includes a parent comment and at least one reply to the parent comment.
15. The non-transitory computer-readable medium of claim 11 , wherein each comment in the plurality of comments is associated with a value that indicates a number of users that agree with the comment.