Automatically generating datasets by processing collaboration forums using artificial intelligence techniques

A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

• obtain conversational data from one or more collaboration forum sources, wherein the conversational data comprise structured data and unstructured data;
• classify, using a first set of one or more artificial intelligence techniques, at least a portion of the obtained conversational data into one or more categories based at least in part on one or more designated applications,
• wherein using the first set of one or more artificial intelligence techniques comprises mapping, using at least one LSTM network, the at least a portion of the obtained conversational data to one or more application tasks associated with the one or more categories;
• extract information, pertaining to one or more test case-related issues, from at least a portion of the classified conversational data;
• verify at least a portion of the extracted information by analyzing, using a second set of one or more artificial intelligence techniques, portions of the conversational data attributed to multiple entities and related to the extracted information;
• generate, using the verified information, one or more datasets related to at least one of the one or more test case-related issues for at least one of the one or more designated applications;
• and
• perform at least one automated action based at least in part on the one or more generated datasets, wherein performing at least one automated actions comprises automatically executing feature testing for at least one of the one or more designated applications using at least one of the one or more generated datasets.

A system comprising:

• a memory configured to store program instructions;
• and
• a processor operatively coupled to the memory to execute the program instructions to:
• obtain conversational data from one or more collaboration forum sources, wherein the conversational data comprise structured data and unstructured data;
• classify, using a first set of one or more artificial intelligence techniques, at least a portion of the obtained conversational data into one or more categories based at least in part on one or more designated applications,
• wherein using the first set of one or more artificial intelligence techniques comprises mapping, using at least one LSTM network, the at least a portion of the obtained conversational data to one or more application tasks associated with the one or more categories;
• extract information, pertaining to one or more test case-related issues, from at least a portion of the classified conversational data;
• verify at least a portion of the extracted information by analyzing, using a second set of one or more artificial intelligence techniques, portions of the conversational data attributed to multiple entities and related to the extracted information;
• generate, using the verified information, one or more datasets related to at least one of the one or more test case-related issues for at least one of the one or more designated applications;
• and
• perform at least one automated action based at least in part on the one or more generated datasets, wherein performing at least one automated actions comprises automatically executing feature testing for at least one of the one or more designated applications using at least one of the one or more generated datasets.