Detecting emotions from micro-expressive free-form movements

A computer-implemented method, comprising:

• at a first time, presenting, on a touchscreen display unit of a communications device and using at least one processor, a user interface of a plurality of predictive models configured to determine emotions that are experienced by users, the user interface including representations of a plurality of default emotions;
• receiving, through the user interface and using the at least one processor, (i) one or more first contacts on the touchscreen display unit, and (ii) data correlating the one or more first contacts with the plurality of default emotions;
• training, using the at least one processor, the plurality of predictive models using the one or more first contacts and the data, to identify one or more default emotions of the plurality of default emotions upon being provided with data corresponding to contacts made with the touchscreen display unit;
• at a second time, receiving, using the at least one processor, first data indicative of a first time-evolving movement of a portion of a body of the user of the communications device during a collection period, wherein the first time-evolving movement comprises a plurality of contacts established sequentially between the portion of the body of the user and a surface of the touchscreen display unit at corresponding first contact times during the collection period;
• determining, using the first data and the at least one processor, first values of features that characterize the contacts during the collection period, wherein the features comprise an X coordinate of the portion of the body, a Y coordinate of the portion of the body, an area of contact of the portion of the body, a contact force of the portion of the body, and a time of movement of the portion of the body;
• accessing second data about the plurality of predictive models that have been trained at the first time, wherein one or more of the plurality of predictive models correlates ranges of second values of one or more of the features obtained during prior collection periods to default emotions of the plurality of default emotions;
• comparing, using the at least one processor and using at least one of a pattern recognition algorithm or a machine learning algorithm, the first values of the features determined using the first data to the second data;
• in response to the comparing, determining, using the at least one processor, that one or more first values are within ranges of second values of one or more features that correlate with a particular default emotion of the plurality of default emotions;
• in response to the determination, associating, using the at least one processor, the one or more first values with a predictive model that corresponds to the particular default emotion;
• based on the associating, determining, using the at least one processor, that the first time-evolving movement of the portion of the body of the user during the collection period indicates that the particular default emotion is experienced by the user during the collection period;
• and
• transmitting, using the at least one processor, data indicative of the particular default emotion to the communications device to present a representation of the corresponding one of the default emotion.

A device, comprising:

• a storage device;
• a touchscreen display unit;
• and one or more sensor devices;
• and
• at least one processor coupled to the storage device, the storage device storing software instructions for controlling the at least one processor when executed by the at least one processor, the at least one processor being operative with the software instructions and being configured to perform the operations of:
• at a first time, presenting, on the touchscreen display unit of a communications device, a user interface of a plurality of predictive models configured to determine emotions that are experienced by users, the user interface including representations of a plurality of default emotions;
• receiving, through the user interface, (i) one or more first contacts on the touchscreen display unit, and (ii) data correlating the one or more first contacts with the plurality of default emotions;
• training the plurality of predictive models using the one or more first contacts and the data, to identify one or more default emotions of the plurality of default emotions upon being provided with data corresponding to contacts made with the touchscreen display unit;
• at a second time, detecting, a first time-evolving movement of a portion of a body of the user of the communications device during a collection period, wherein the first time-evolving movement comprises a plurality of contacts established sequentially between the portion of the body of the user and a surface of the touchscreen display unit at corresponding first contact times during the collection period;
• determining, using data indicative of the detected first time-evolving movement, first values of features that characterize the contacts during the collection period, wherein the features comprise an X coordinate of the portion of the body, a Y coordinate of the portion of the body, an area of contact of the portion of the body, a contact force of the portion of the body, and a time of movement of the portion of the body;
• accessing second data about the plurality of predictive models that have been trained at the first time, wherein one or more of the plurality of predictive models correlates ranges of second values of one or more of the features obtained during prior collection periods to default emotions of the plurality of default emotions;
• comparing, using at least one of a pattern recognition algorithm or a machine learning algorithm, the first values of the features determined using the data indicative of the detected first time-evolving movement to the second data;
• in response to the comparing, determining that one or more first values are within ranges of second values of one or more features that correlate with a particular default emotion of the plurality of default emotions;
• in response to the determination, associating the one or more first values with a predictive model that corresponds to the particular default emotion;
• based on the associating, determining that the first time-evolving movement of the portion of the body of the user during the collection period indicates that the particular default emotion is experienced by the user during the collection period;
• and
• presenting a representation of the particular default emotion.