Data relationships in a question-answering environment

A system for establishing influence relationships between data in a question-answering environment, the system comprising:

• a processor;
• and
• a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the processor to cause the system to:
• receive an electronic text document from a user over a network;
• parse, using a natural language processor, the electronic text document to determine a set of conditions indicating a set of user statuses, wherein parsing, using the natural language processor, the electronic text document to determine the set of conditions includes:
• converting sequences of characters within the electronic text document into tokens;
• determining a set of repeated words in the electronic text document;
• determining a location of each of the repeated words in the set of repeated words;
• and
• selecting, based on the location of each of the repeated words of the set of repeated words, a subset of repeated words, wherein the set of conditions are selected based on the subset of repeated words;
• access, over the network, a corpus of data including a set of user data;
• analyze, using the natural language processor, the corpus of data including the set of user data;
• identify, based on analyzing the corpus of data, a set of influence factors corresponding to a subset of the set of user data and to a subset of the set of conditions, wherein identifying the set of influence factors corresponding to the subset of the set of user data and to the subset of the set of conditions includes:
• identifying, by the natural language processor, a first characteristic of a first data type of the subset of the set of user data, the first data type in a first format;
• assigning a first weight to the first characteristic based on the first data type and the first format;
• identifying, by the natural language processor, a second characteristic of a second data type of the subset of the set of user data, the second data type in a second format;
• assigning a second weight to the second characteristic based on the second data type and the second format;
• identifying a first influence factor of the set of influence factors using the first characteristic and the second characteristic;
• and
• assigning a third weight to the first influence factor based on the first weight of the first characteristic and the second weight of the second characteristic;
• establish, based on the set of influence factors, a set of influence relationships between the subset of the set of user data and the subset of the set of conditions, wherein a first influence relationship is established using the first influence factor;
• and
• generate an explanation for the subset of conditions using at least the first influence relationship based on the third weight of the first influence factor.

A computer program product for establishing influence relationships between data in a question-answering environment, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

• receiving an electronic text document from a user over a network;
• parsing, using a natural language processor, the electronic text document to determine a set of conditions indicating a set of user statuses, wherein parsing, using the natural language processor, the electronic text document to determine the set of conditions includes:
• converting sequences of characters within the electronic text document into tokens;
• determining a set of repeated words in the electronic text document;
• determining a location of each of the repeated words in the set of repeated words;
• and
• selecting, based on the location of each of the repeated words of the set of repeated words, a subset of repeated words, wherein the set of conditions are selected based on the subset of repeated words;
• accessing, over the network, a corpus of data including a set of user data;
• analyzing, using the natural language processor, the corpus of data including the set of user data;
• identifying, based on analyzing the corpus of data, a set of influence factors corresponding to a subset of the set of user data and to a subset of the set of conditions, wherein identifying the set of influence factors corresponding to the subset of the set of user data and to the subset of the set of conditions includes:
• identifying, by the natural language processor, a first characteristic of a first data type of the subset of the set of user data, the first data type in a first format;
• assigning a first weight to the first characteristic based on the first data type and the first format;
• identifying, by the natural language processor, a second characteristic of a second data type of the subset of the set of user data, the second data type in a second format;
• assigning a second weight to the second characteristic based on the second data type and the second format;
• identifying a first influence factor of the set of influence factors using the first characteristic and the second characteristic;
• and
• assigning a third weight to the first influence factor based on the first weight of the first and the second weight of the second characteristic;
• establishing, based on the set of influence factors, a set of influence relationships between the subset of the set of user data and the subset of the set of conditions, wherein a first influence relationship is established using the first influence factor;
• and
• generating an explanation for the subset of conditions using at least the first influence relationship based on the third weight of the first influence factor.