# US 10,311,143 B2 · Preventing frustration in online chat communication > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,143 B2 - Document ID: US10311143B2 - Status: Granted - Kind: B2 - Application number: 15/651,371 - Filed: 2017-07-17 - Published: 2017-11-02 - Granted: 2019-06-04 - Earliest claimed: 2013-04-23 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Annemarie R. Fitterer; Ramakrishna J. Gorthi; Chandrajit G. Joshi; Romil J. Shah - Web page: https://patentgrep.com/patent/US10311143B2 ## CPC - G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking - G06F 40/10: Text processing (natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40) - G06F 40/242: Dictionaries - G06F 40/30: Semantic analysis - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Frustration in online chat communication is prevented in which a text transcript is generated by at least two chat participants, by: (i) identifying in a text transcript a text-based signal listed on a list of text-based signals in a table; (ii) performing a first text analytics analysis on the text transcript to determine whether potential frustration is evidenced by the text transcript, the first text analytics analysis using a context hint provided in the table, the context hint corresponding in the table to the text-based signal; and (iii) responsive to potential frustration being evidenced by the text transcript, taking a responsive action based at least in part upon a potential cause of the potential frustration determined by performing a second text analytics analysis on the text transcript. The context hint is a contextual clue that supports a determination of whether the text-based signal indicates potential frustration as evidenced by the text transcript. ## Claims ### Claim 1 A method comprising: identifying in a text transcript of a synchronous computer-mediated communication by at least two chat participants including a first chat participant and a second chat participant a text-based signal listed on a list of text-based signals in a table; performing a first text analytics analysis on the text transcript to determine whether potential frustration is evidenced by the text transcript, the first text analytics analysis using a context hint provided in the table, the context hint corresponding in the table to the text-based signal; and responsive to potential frustration being evidenced by the text transcript, taking a responsive action based at least in part upon a potential cause of the potential frustration determined by performing a second text analytics analysis on the text transcript; wherein: the context hint is a contextual clue that, if found within the text transcript, supports a determination of whether the text-based signal indicates potential frustration as evidenced by the text transcript; the table includes a user-specific portion that is customizable by the first chat participant to include participant-specific text-based signals corresponding to the second chat participant; and the user-specific portion being customizable to indicate a participant-specific potential frustration precondition corresponding to the second chat participant during a chat session between the first chat participant and the second chat participant. ### Claim 2 (depends on 1) The method of claim 1, wherein the responsive action includes automatically, and under software control, making a suggestion to at least one of the at least two chat participants with respect to how the communication may be conducted. ### Claim 3 (depends on 1) The method of claim 1, wherein: the table includes a global portion and a local portion; the global portion includes a set of global text-based signals pre-determined by a group policy; and the local portion includes a set of local text-based signals input by a first participant to supplement the set of global text-based signals and/or to exclude a global text-based signal from the set of global text-based signals. ### Claim 4 (depends on 1) The method of claim 1, wherein: the potential cause is a subject matter content type; and the responsive action is to take no action. ### Claim 5 (depends on 1) The method of claim 1, wherein the second text analytics analysis includes: retrieving a responsive action table that includes a set of recommended responsive actions respectively corresponding to the list of text-based signals. ### Claim 6 (depends on 1) The method of claim 1, wherein the responsive action is further based at least in part upon employment data of one of the at least two chat participants. ### Claim 7 (depends on 1) The method of claim 1, wherein the responsive action is designed to alleviate an occurrence of potential frustration for the second chat participant. ### Claim 8 A computer program product comprising software stored on a non-transitory computer-readable storage medium, the software comprising: first program instructions programmed to identify in a text transcript of a synchronous computer-mediated communication by at least two chat participants including a first chat participant and a second chat participant a text-based signal listed on a list of text-based signals in a table; second program instructions programmed to perform a first text analytics analysis on the text transcript to determine whether potential frustration is evidenced by the text transcript, the first text analytics analysis using a context hint provided in the table, the context hint corresponding in the table to the text-based signal; and third program instructions programmed to, responsive to potential frustration being evidenced by the text transcript, take a responsive action based at least in part upon a potential cause of the potential frustration determined by performing a second text analytics analysis on the text transcript; wherein: the context hint is a contextual clue that, if found within the text transcript, supports a determination of whether the text-based signal indicates potential frustration as evidenced by the text transcript; the table includes a user-specific portion that is customizable by the first chat participant to include participant-specific text-based signals corresponding to the second chat participant; and the user-specific portion being customizable to indicate a participant-specific potential frustration precondition corresponding to the second chat participant during a chat session between the first chat participant and the second chat participant. ### Claim 9 (depends on 8) The computer program product of claim 8, wherein the responsive action includes automatically, and under software control, making a suggestion to at least one of the at least two chat participants with respect to how the communication may be conducted. ### Claim 10 (depends on 8) The computer program product of claim 8, wherein: the table includes a global portion and a local portion; the global portion includes a set of global text-based signals pre-determined by a group policy; and the local portion includes a set of local text-based signals input by a first participant to supplement the set of global text-based signals and/or to exclude a global text-based signal from the set of global text-based signals. ### Claim 11 (depends on 8) The computer program product of claim 8, wherein: the potential cause is a subject matter content type; and the responsive action is to take no action. ### Claim 12 (depends on 8) The computer program product of claim 8, wherein the second text analytics analysis includes: retrieving a responsive action table that includes a set of recommended responsive actions respectively corresponding to the list of text-based signals. ### Claim 13 (depends on 8) The computer program product of claim 8, wherein the responsive action is further based at least in part upon employment data of one of the at least two chat participants. ### Claim 14 (depends on 8) The computer program product of claim 8, wherein the responsive action is designed to alleviate an occurrence of potential frustration for the second chat participant. ### Claim 15 A computer system comprising: a processor set; and a non-transitory computer readable storage medium; wherein: the processor set is structured, located, connected, and/or programmed to run program instructions stored on the non-transitory computer readable storage medium; and the program instructions include: first program instructions programmed to identify in a text transcript of a synchronous computer-mediated communication by at least two chat participants including a first chat participant and a second chat participant a text-based signal listed on a list of text-based signals in a table; second program instructions programmed to perform a first text analytics analysis on the text transcript to determine whether potential frustration is evidenced by the text transcript, the first text analytics analysis using a context hint provided in the table, the context hint corresponding in the table to the text-based signal; and third program instructions programmed to, responsive to potential frustration being evidenced by the text transcript, take a responsive action based at least in part upon a potential cause of the potential frustration determined by performing a second text analytics analysis on the text transcript; wherein: the context hint is a contextual clue that, if found within the text transcript, supports a determination of whether the text-based signal indicates potential frustration as evidenced by the text transcript; the table includes a user-specific portion that is customizable by the first chat participant to include participant-specific text-based signals corresponding to the second chat participant; and the user-specific portion being customizable to indicate a participant-specific potential frustration precondition corresponding to the second chat participant during a chat session between the first chat participant and the second chat participant. ### Claim 16 (depends on 15) The computer system of claim 15, wherein the responsive action includes automatically, and under software control, making a suggestion to at least one of the at least two chat participants with respect to how the communication may be conducted. ### Claim 17 (depends on 15) The computer system of claim 15, wherein: the table includes a global portion and a local portion; the global portion includes a set of global text-based signals pre-determined by a group policy; and the local portion includes a set of local text-based signals input by a first participant to supplement the set of global text-based signals and/or to exclude a global text-based signal from the set of global text-based signals. ### Claim 18 (depends on 15) The computer system of claim 15, wherein: the potential cause is a subject matter content type; and the responsive action is to take no action. ### Claim 19 (depends on 15) The computer system of claim 15, wherein the second text analytics analysis includes: retrieving a responsive action table that includes a set of recommended responsive actions respectively corresponding to the list of text-based signals. ### Claim 20 (depends on 15) The computer system of claim 15, wherein the responsive action is designed to alleviate an occurrence of potential frustration for the second chat participant.