Device and method and program of text analysis based on change points of time-series signals

A text analysis method comprising the steps of:

• generating feature quantity data of text data stored in storage means which stores opinions of users who participate in a discussion about a predetermined theme as the text data and author information for specifying authors of the text data;
• generating observation time-series signals based on information obtained by performing a predetermined process with respect to the feature quantity data;
• learning the observation time-series signals to specify node labels of the text data;
• generating a time-series node pattern in which the node labels are arranged in order corresponding to the observation time-series signals;
• detecting a change point of the discussion based on the time-series node pattern;
• and
• specifying an opinion having influence on an opinion corresponding to the specified text data out of opinions of the discussion based on the detected change point and the author information.

A non-transitory computer-readable medium storing a program which enables a computer to execute:

• generating feature quantity data of text data stored in storage means which stores opinions of users who participate in a discussion about a predetermined theme as text data and author information for specifying authors of the text data;
• generating observation time-series signals based on information obtained by performing a predetermined process with respect to the feature quantity data;
• learning the observation time-series signals to specify node labels of the text data;
• generating a time-series node pattern in which the node labels are arranged in order corresponding to the observation time-series signals;
• detecting a change point of the discussion based on the time-series node pattern;
• and
• specifying an opinion having influence on an opinion corresponding to the specified text data out of opinions of the discussion based on the detected change point and the author information.

A text analysis device comprising:

• a storage unit configured to store opinions of users who participate in a discussion about a predetermined theme as text data and author information for specifying authors of the text data;
• a feature quantity data generation unit configured to generate feature quantity data of the text data stored in the storage unit;
• an observation time-series signal generation unit configured to generate observation time-series signals based on information obtained by performing a predetermined process with respect to the feature quantity data;
• a time-series node pattern generation unit configured to learn the observation time-series signals to specify node labels of the text data and to generate a time-series node pattern in which the node labels are arranged in order corresponding to the observation time-series signals;
• a change point detection unit configured to detect a change point of the discussion based on the time-series node pattern;
• and
• an influence specifying unit configured to specify an opinion having influence on an opinion corresponding to the specified text data out of opinions of the discussion based on the detected change point and the author information.