Method and apparatus for generating information

An apparatus for generating information, comprising:

• at least one processor;
• and
• a memory storing instructions, wherein the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
• acquiring to-be-analyzed information according to a target keyword;
• and
• inputting the to-be-analyzed information into a pre-established sentiment analysis model to generate sentiment orientation information of the to-be-analyzed information, the generating unit comprising:
• acquiring untagged sample data and tagged sample data;
• generating tag information corresponding to the untagged sample data using a pre-established tag generation model, and use the untagged sample data and the generated tag information as extended sample data, the tag information including a first tag, a second tag, and a third tag, and the tag generation model being used to represent a corresponding relationship between the untagged sample data and the tag information;
• and
• obtaining the sentiment analysis model by training using the tagged sample data and the extended sample data.

A non-transitory computer storage medium, storing a computer program, wherein the computer program, when executed by a processor, causes the processor to perform operations, the operations comprising:

• acquiring to-be-analyzed information according to a target keyword;
• and
• inputting the to-be-analyzed information into a pre-established sentiment analysis model to generate sentiment orientation information of the to-be-analyzed information, the sentiment analysis model being obtained through following training:
• acquiring untagged sample data and tagged sample data;
• generating tag information corresponding to the untagged sample data using a pre-established tag generation model, and using the untagged sample data and the generated tag information as extended sample data, the tag information including a first tag, a second tag, and a third tag, and the tag generation model being used to represent a corresponding relationship between the untagged sample data and the tag information;
• and
• obtaining the sentiment analysis model by training using the tagged sample data and the extended sample data.