Suggestion of communication styles personalized to target audience in a text editor

One or more non-transitory computer-readable media storing one or more sequences of instructions which, when executed using a first computer, cause the first computer to execute:

• programmatically receiving a digital electronic object, the digital electronic object comprising a source text that is directed to a target audience and that was composed at a second computer;
• determining, based on a communication profile of the target audience, a style value specifying a particular communication style from among a plurality of different communication styles;
• evaluating the source text using a trained machine-learning model by dividing the source text into one or more source text units and inputting the one or more source text units into the machine-learning model;
• receiving a classification output from the machine-learning model comprising one or more source text style values specifying the particular communication style for the one or more source text units, respectively;
• generating, by the machine-learning model, a modified text based on applying one or more candidate edits to one or more of the source text units of the source text, the modified text having been classified using the particular communication style specified in the style value, wherein the one or more candidate edits are determined based on the style value and the one or more source text style values;
• generating an output set of suggested edits to the source text based on the one or more candidate edits;
• transmitting the output set of suggested edits to the second computer.

A computing device programmed for text processing and comprising:

• one or more central processing units;
• one or more network interfaces that are configured to communicatively couple the one or more central processing units to a data communication network;
• electronic digital random access memory storing a plurality of sequences of stored program instructions that are organized as executable checks for checking a digitally stored source text that is received via the data communication network from a computing device that is executing a text processing extension, a style check among the executable checks comprising multi-class text classifier instructions coupled to style suggestion instructions, the style suggestion instructions being coupled to a digital phrase store;
• the multi-class text classifier instructions and style suggestion instructions being programmed to read the source text;
• determine, based on a communication profile of a target audience that the source text is directed to, a style value specifying a particular communication style from among a plurality of different communication styles;
• evaluate the source text using a trained machine-learning model by dividing the source text into one or more source text units and inputting the one or more source text units into the machine-learning model;
• receive a classification output from the machine-learning model comprising one or more source text style values specifying the particular communication style for the one or more source text units, respectively;
• generate, by the machine-learning model, a modified text based on applying one or more candidate edits to one or more of the source text units of the source text, the modified text having been classified using the particular communication style specified in the style value, wherein the one or more candidate edits are determined based on the style value and the one or more source text style values;
• generate an output set of suggested edits to the source text based on the one or more candidate edits;
• transmit the output set of suggested edits to the computing device via the data communication network.