Message topic classification agent
This is an agent that performs the message classification by topic (greeting, about lab work condition, about entity etc.). Also, the agent classifies message by trait (neutral, positive, negative emotional coloring) and gets message entities. The agent classifies a message using Wit.ai.
Action class:
action_message_topic_classification
Parameters:
messageAddr
-- an element ofconcept_message
.
Libraries used:
- Wit.ai - to classify message and get entities.
Comment:
- The input message must contain a text file with the text in Russian;
- The excluding entity should be formalized in knowledge base.
Examples
Examples of an input structure:
Examples of an output structure:
Example of a structure needed to classify message by intent:
Example of a structure needed to classify message by trait:
Example of a structure needed to get message entity:
Message classes:
concept_greeting_message
concept_message_about_entity
concept_message_about_subdividing
concept_message_about_study_system
concept_message_about_lab_work_condition
concept_message_about_lab_work_deadline
Agent implementation language
C++
Result
Possible result codes:
SC_RESULT_OK
- the message is successfully classified (or there is empty classification) or the action doesn't belong to the action_message_topic_classification.SC_RESULT_ERROR
- internal error.