Recommendation generator responsive to messaging content

A system, comprising:

• a processor;
• a computer readable memory in circuit communication with the processor;
• and
• a computer readable storage medium in circuit communication with the processor;
• wherein the processor executes program instructions stored on the computer-readable storage medium via the computer readable memory and thereby:
• extracts text content from a received message in response to receipt of the message from a messaging application that is directed from a sender to a recipient within the messaging application;
• identifies a keyword within the extracted text content that is assigned to a topic leaf node within an event taxonomy;
• identifies a root event node within the event taxonomy from which the topic leaf node depends within the event taxonomy;
• identifies a plurality of recommendation items that each match a type of event of the root event node and are linked to the topic node of the identified keyword;
• determines, for each of the recommendation items, a sender sentiment value as a function of a preference of the sender, and a recipient sentiment value as a function of a preference of the recipient;
• presents to the sender and the recipient as an event recommendation a subset of the recommendation items that each satisfy a sentiment threshold for the sender sentiment value and the recipient sentiment value, which assigns one of a positive sentiment value and a negative sentiment value to each of the recommendation items for the sender as a function of a respective preferences indicated by the sender with respect to each of the recommendation items, assigns one of the positive sentiment value and the negative sentiment value to each of the recommendation items for the recipient as a function of a respective preferences indicated by the recipient with respect to each of the recommendation items, for each of the recommendation items, generates consensus sentiment values by adding respective ones of the sentiment values assigned for the sender and the recipient, and selects and presents to the sender and recipient as the event recommendation a subset of the recommendation items that each have consensus sentiment values that meet or exceed a sentiment threshold value;
• in response to determining that the sender and recipient have not agreed on selection of the event recommendation subset items presented to the sender and recipient, updates the preference profile data of the sender and the recipient with negative sentiment values for each of the presented event recommendation subset items;
• in response to determining that the sender and recipient have not agreed on selection of the event recommendation subset items presented to the sender and recipient, updates the preference profile data of the sender and the recipient with negative sentiment values for each of the presented event recommendation subset items;
• and
• iteratively repeats, until the sender and recipient agree on selection of a recommendation item presented within a current event recommendation subset, assigning the positive or negative sentiments value to each of the recommendation items as a function of the updated preference profile data of the sender and the recipient, generating the consensus sentiment values for the sender and the recipient, and presenting to the sender and the recipient as the event recommendation the subset of the recommendation items that each satisfy the sentiment threshold for the sender sentiment value and the recipient sentiment value.

A computer program product for recommendation generation in response to messaging content, the computer program product comprising:

• a computer readable storage medium having computer readable program code embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the computer readable program code comprising instructions for execution by a processor that cause the processor to:
• extract text content from a received message in response to receipt of the message from a messaging application that is directed from a sender to a recipient within the messaging application;
• identify a keyword within the extracted text content that is assigned to a topic leaf node within an event taxonomy;
• identify a root event node within the event taxonomy from which the topic leaf node depends within the event taxonomy;
• identify a plurality of recommendation items that each match a type of event of the root event node and are linked to the topic node of the identified keyword;
• determine, for each of the recommendation items, a sender sentiment value as a function of a preference of the sender, and a recipient sentiment value as a function of a preference of the recipient;
• present to the sender and the recipient as an event recommendation a subset of the recommendation items that each satisfy a sentiment threshold for the sender sentiment value and the recipient sentiment value, which comprises:
• assigning one of a positive sentiment value and a negative sentiment value to each of the recommendation items for the sender as a function of a respective preferences indicated by the sender with respect to each of the recommendation items, assigning one of the positive sentiment value and the negative sentiment value to each of the recommendation items for the recipient as a function of a respective preferences indicated by the recipient with respect to each of the recommendation items, for each of the recommendation items, generating consensus sentiment values by adding respective ones of the sentiment values assigned for the sender and the recipient, and selecting and presenting to the sender and recipient as the event recommendation a subset of the recommendation items that each have consensus sentiment values that meet or exceed a sentiment threshold value;
• in response to determining that the sender and recipient have not agreed on selection of the event recommendation subset items presented to the sender and recipient, update preference profile data of the sender and the recipient with negative sentiment values for each of the presented event recommendation subset items;
• and
• iteratively repeat, until the sender and recipient agree on selection of a recommendation item presented within a current event recommendation subset, assigning the positive or negative sentiments value to each of the recommendation items as a function of the updated preference profile data of the sender and the recipient, generating the consensus sentiment values for the sender and the recipient, and presenting to the sender and the recipient as the event recommendation the subset of the recommendation items that each satisfy the sentiment threshold for the sender sentiment value and the recipient sentiment value.