# US 12,222,968 B2 · Detecting emotional events in textual content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,222,968 B2 - Document ID: US12222968B2 - Status: Granted - Kind: B2 - Application number: 18/345,038 - Filed: 2023-06-30 - Published: 2025-01-02 - Granted: 2025-02-11 - Earliest claimed: 2023-06-30 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Mikael Hillborg; Linjing Fu; Joshua Bello; Aderinsola Okunoren - Web page: https://patentgrep.com/patent/US12222968B2 ## CPC - G06F 16/285: {Clustering or classification} - G06F 16/35: Clustering; Classification - G06F 18/24765: {Rule-based classification} - G06F 40/295: Named entity recognition - G06F 40/30: Semantic analysis - G06F 40/205: Parsing - G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Computer implemented methods, systems, and computer program products include program code executing on a processor(s) that obtains text from a computing resources in a domain and segments it into sentences. The processor(s) identifies entities in each sentence. The processor(s) classifies each entity with a sentiment (a polarity). The processor(s) identifies, for each sentence, a given entity with a strongest sentiment. The processor(s) derives for each sentence, for each entity, emotions and classifies each emotion by assigning a polarity to each and scoring each. The processor(s) calculates, based on the (emotion) scores, a mean and a standard deviation from the mean. The processor(s) maps the given entity for each sentence to a strongest emotion for the given entity where the polarity of the strongest emotion is the same as the polarity of the strongest sentiment. The processor(s) determines if each strongest emotion is within the standard deviation from the mean. ## Claims ### Claim 1 A computer-implemented method of identifying key emotional content in a text, the method comprising: obtaining, by one or more processors, the text from a computing resource in a domain; segmenting, by the one or more processors, the text into sentences; utilizing, by the one or more processors, pre-defined entities for the domain, to identify entities in each sentence of the sentences comprising the text; classifying, by the one or more processors, each entity of the identified entities with a sentiment and extracting the sentiments, wherein the classifying assigns a polarity to each sentiment of the sentiments; identifying, by the one or more processors, for each sentence, a given entity with a strongest sentiment, wherein the identifying comprises quantitively determining a value for each of the sentiments and utilizing the values to identify the strongest sentiment; deriving, by the one or more processors, for each sentence, for each entity, one or more emotions and classifying each emotion of the one or more emotions, wherein the classifying comprising: assigning a polarity to each emotion; and associating a score with each emotion to reflect a strength of each emotion within the polarity; calculating, by the one or more processors, for the one or more emotions in each sentence of the text, based on the scores, a mean and a standard deviation from the mean; mapping, by the one or more processors, the given entity for each sentence to a strongest emotion for the given entity, wherein the polarity of the strongest emotion for each given entity is the same as the polarity of the strongest sentiment for the given entity; determining, by the one or more processors, for each strongest emotion, if the strongest emotion is within the standard deviation from the mean; and based on determining that a strongest emotion of the strongest emotions is within the standard deviation from the mean, retaining the strongest emotion. ### Claim 2 (depends on 1) The method of claim 1, further comprising: providing, by the one or more processors, a visualization of the strongest emotion as output to indicate a key emotional content in the text. ### Claim 3 (depends on 1) The method of claim 1, wherein the determining, for each strongest emotion, if the strongest emotion is within the standard deviation from the mean comprises: evaluating, by the one or more processors, each strongest emotion for each sentence sequentially; and retaining, by the one or more processors, each strongest emotion within the standard deviation from the mean. ### Claim 4 (depends on 3) The method of claim 3, further comprising: generating, by the one or more processors, a model representing of each strongest emotion within the standard deviation from the mean; and providing, by the one or more processors, the model as output, wherein the output indicates key emotional content in the text. ### Claim 5 (depends on 1) The method of claim 1, wherein the pre-defined entities for the domain are retained in a memory accessible to the one or more processors, and wherein each pre-defined entity represents a key role in the domain. ### Claim 6 (depends on 1) The method of claim 1, wherein the polarity of each sentiment and the polarity of each emotion is selected from the group consisting of: positive and negative. ### Claim 7 (depends on 1) The method of claim 1, wherein the polarity of each sentiment and the polarity of each emotion is selected from the group consisting of: positive, neutral, and negative. ### Claim 8 (depends on 1) The method of claim 1, wherein each emotion of the one or more emotions is selected from the group consisting of: anger, disgust, fear, joy, and sadness. ### Claim 9 (depends on 1) The method of claim 1, wherein the score associated with each emotion is from 0 to 1. ### Claim 10 (depends on 7) The method of claim 7, wherein mapping the given entity for each sentence comprises, for each given entity: determining, by the one or more processors, that the strongest sentiment for the given entity is positive; and mapping the given entity to a strongest positive emotion for the given entity. ### Claim 11 (depends on 7) The method of claim 7, wherein mapping the given entity for each sentence comprises, for each given entity: determining, by the one or more processors, that the strongest sentiment for the given entity is negative; and mapping the given entity to a strongest negative emotion for the given entity. ### Claim 12 (depends on 7) The method of claim 7, wherein mapping the given entity for each sentence comprises, for each given entity: determining, by the one or more processors, that the strongest sentiment for the given entity is neutral; and mapping the given entity to a strongest emotion for the given entity. ### Claim 13 A computer system for determining resource dispositions for identifying key emotional content in a text, the computer system comprising: a memory; and one or more processors in communication with the memory, wherein the computer system is configured to perform a method, said method comprising: obtaining, by the one or more processors, the text from a computing resource in a domain; segmenting, by the one or more processors, the text into sentences; utilizing, by the one or more processors, pre-defined entities for the domain, to identify entities in each sentence of the sentences comprising the text; classifying, by the one or more processors, each entity of the identified entities with a sentiment and extracting the sentiments, wherein the classifying assigns a polarity to each sentiment of the sentiments; identifying, by the one or more processors, for each sentence, a given entity with a strongest sentiment, wherein the identifying comprises quantitively determining a value for each of the sentiments and utilizing the values to identify the strongest sentiment; deriving, by the one or more processors, for each sentence, for each entity, one or more emotions and classifying each emotion of the one or more emotions, wherein the classifying comprising: assigning a polarity to each emotion; and associating a score with each emotion to reflect a strength of each emotion within the polarity; calculating, by the one or more processors, for the one or more emotions in each sentence of the text, based on the scores, a mean and a standard deviation from the mean; mapping, by the one or more processors, the given entity for each sentence to a strongest emotion for the given entity, wherein the polarity of the strongest emotion for each given entity is the same as the polarity of the strongest sentiment for the given entity; determining, by the one or more processors, for each strongest emotion, if the strongest emotion is within the standard deviation from the mean; and based on determining that a strongest emotion of the strongest emotions is within the standard deviation from the mean, retaining the strongest emotion. ### Claim 14 (depends on 13) The computer system of claim 13, further comprising: providing, by the one or more processors, a visualization of the strongest emotion as output to indicate a key emotional content in the text. ### Claim 15 (depends on 13) The computer system of claim 13, wherein the determining, for each strongest emotion, if the strongest emotion is within the standard deviation from the mean comprises: evaluating, by the one or more processors, each strongest emotion for each sentence sequentially; and retaining, by the one or more processors, each strongest emotion within the standard deviation from the mean. ### Claim 16 (depends on 15) The computer system of claim 15, further comprising: generating, by the one or more processors, a model representing of each strongest emotion within the standard deviation from the mean; and providing, by the one or more processors, the model as output, wherein the output indicates key emotional content in the text. ### Claim 17 (depends on 13) The computer system of claim 13, wherein the pre-defined entities for the domain are retained in a storage device accessible to the one or more processors, and wherein each pre-defined entity represents a key role in the domain. ### Claim 18 A computer program product for identifying key emotional content in a text, the computer program product comprising: one or more computer readable storage media and program instructions collectively stored on the one or more computer readable storage media readable by at least one processing circuit to: obtain, by the one or more processors, the text from a computing resource in a domain; segment, by the one or more processors, the text into sentences; utilize, by the one or more processors, pre-defined entities for the domain, to identify entities in each sentence of the sentences comprising the text; classify, by the one or more processors, each entity of the identified entities with a sentiment and extracting the sentiments, wherein the classifying assigns a polarity to each sentiment of the sentiments; identify, by the one or more processors, for each sentence, a given entity with a strongest sentiment, wherein the identifying comprises quantitively determining a value for each of the sentiments and utilizing the values to identify the strongest sentiment; derive, by the one or more processors, for each sentence, for each entity, one or more emotions and classifying each emotion of the one or more emotions, wherein the classifying comprising: assign a polarity to each emotion; and associate a score with each emotion to reflect a strength of each emotion within the polarity; calculate, by the one or more processors, for the one or more emotions in each sentence of the text, based on the scores, a mean and a standard deviation from the mean; map, by the one or more processors, the given entity for each sentence to a strongest emotion for the given entity, wherein the polarity of the strongest emotion for each given entity is the same as the polarity of the strongest sentiment for the given entity; determine, by the one or more processors, for each strongest emotion, if the strongest emotion is within the standard deviation from the mean; and based on determining that a strongest emotion of the strongest emotions is within the standard deviation from the mean, retain the strongest emotion.