# US 12,769,800 B2 · Method and system of identifying and allocating sentiment attribution > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,769,800 B2 - Document ID: US12769800B2 - Status: Granted - Kind: B2 - Application number: 18/677,965 - Filed: 2024-05-30 - Published: 2024-10-31 - Granted: 2026-10-20 - Earliest claimed: 2018-12-11 - Applicants: Vaibhav Bhan - Inventors: Vaibhav Bhan - Web page: https://patentgrep.com/patent/US12769800B2 ## CPC - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 16/24578: {using ranking} - G06F 16/9536: Search customisation based on social or collaborative filtering - G06Q 10/40: Business processes related to social networking or social networking services - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract A method and system, performed in a server computing device, of identifying and allocating sentiment attributions. The method comprises detecting, using a semantic similarity analysis, content associated with a plurality of subjects of interest, the content including a sentiment expressive usage associated with the plurality of subjects of interest and being characterized in accordance with a sentiment parameter associated with a net sentiment score, identifying, based on continuously monitoring the subjects of interest upon accessing, by the processor, a linguistic framework that includes a sentiment identification component and a sentiment intensity rating associated with the at least one sentiment parameter in accordance with sentiment expressive usage, determining a first and at least a second portions of the net sentiment score that is attributable to the first and the at least a second subjects of interest respectively, and generating engagement actions with regard to the respective subjects of interest. ## Claims ### Claim 1 A method of attributing portions of a sentiment score (NSS) generated in a transient sentiment community within a distributed communication network, the method performed in a computing system communicatively connected within the distributed communication network, the method comprising: detecting, based at least in part upon a semantic similarity analysis performed in a processor of the computing system, content associated with a plurality of subjects of interest, the content defined in accordance with at least one text character string that is included within social media content data received at the computing system, the content including a sentiment expression associated with the plurality of subjects of interest, the sentiment expressive usage being characterized in accordance with at least one sentiment parameter associated with the sentiment score; identifying, based on continuously monitoring, by the processor, a first and at least a second subjects of interest of the plurality upon accessing, by the processor, a sentiment identification component stored in a memory of the computing system and a sentiment intensity rating associated with the at least one sentiment parameter in accordance with the sentiment expression; determining, responsive to identifying the first and at least a second subjects of interest, a first and at least a second portions of the sentiment score that is attributable to the first and the at least a second subjects of interest respectively; and triggering, based on transmission to a community that receives the social media content data over the distributed computing network, an evidential gathering of facts in rebuttal of the sentiment expression, the evidential gathering being directed to one or more assertions associated with the sentiment expression. ### Claim 2 (depends on 1) The method of claim 1 wherein the social media content comprises one or more of: a hashtag, a twitter handle, an emoticon, at least a portion of a website content, a text string produced via a speech to text conversion of at least a portion of an audio file, a message exchange, an image, and at least a video portion. ### Claim 3 (depends on 2) The method of claim 2 wherein the plurality of subjects of interest comprises one or more of a named product, a named feature, a named brand, a named entity, a named individual, and a named organizational group. ### Claim 4 (depends on 1) The method of claim 1 wherein the sentiment score is determined based on (i) a sentiment score in accordance with the sentiment intensity rating and (ii) an engagement score. ### Claim 5 (depends on 4) The method of claim 4 wherein the sentiment score is determined in accordance with a trained neural network machine learning model in conjunction with the social media content. ### Claim 6 (depends on 4) The method of claim 4 wherein the first and at least a second portions of the sentiment score that is attributable to the first and the at least a second subjects of interest respectively are determined based respective sentiment scores and engagement scores. ### Claim 7 (depends on 6) The method of claim 6 wherein at least one of the first and the at least a second engagement actions are generated upon reaching at least one of: (i) a predetermined threshold of the sentiment score; (ii) a rate of growth of the transient sentiment community that receives the content and the sentiment expression; (iii) respective predetermined sentiment attribution thresholds associated with the first and at least a second portions; and (iv) a rate of growth of the NSS over at least a period of time. ### Claim 8 (depends on 6) The method of claim 6 wherein generating at least one of the first and at least a second engagement actions comprises: accessing, by the processor of the computing system, a fact check engine; receiving a fact check result for at least one of the first and the at least second of the subjects of interest from the fact check engine in accordance with the sentiment expression; and transmitting, to the community that receives the social media content data over the distributed computing network, the rebuttal of the sentiment expression based at least in part on the fact check result. ### Claim 9 (depends on 8) The method of claim 8 further comprising: identifying one or more sources of dissemination of one or more assertions associated with at least one of the first and the at least a second subjects of interest; and retaining, as potential evidence in a reputation based legal or administrative proceeding, time stamped information associated with the one or more sources, at least some portions of the social media content, and the fact check results. ### Claim 10 (depends on 1) The method of claim 1 wherein the at least one sentiment parameter comprises a sarcasm sentiment classification, and further comprising determining the first and at least a second portions of the sentiment score attributable to the first and the at least a second subjects of interest respectively based at least in part upon replacing the sarcasm sentiment classification with one of a contrary and an opposite sentiment classification. ### Claim 11 A server computing system comprising: a processor; a memory storing a set of instructions, the instructions when executed in the processor causing the processor to implement operations comprising: detecting, based at least in part upon a semantic similarity analysis performed in a processor of the computing system, content associated with a plurality of subjects of interest, the content defined in accordance with at least one text character string that is included within social media content data received at the computing system, the content including a sentiment expression associated with the plurality of subjects of interest, the sentiment expression being characterized in accordance with at least one sentiment parameter associated with a sentiment score (NSS); identifying, based on continuously monitoring, by the processor, a first and at least a second subjects of interest of the plurality upon accessing, by the processor, a sentiment identification component stored in a memory of the computing system and a sentiment intensity rating associated with the at least one sentiment parameter in accordance with the sentiment expression; determining, responsive to identifying the first and at least a second subjects of interest, a first and at least a second portions of the sentiment score that is attributable to the first and the at least a second subjects of interest respectively; and triggering, based on transmission to a community that receives the social media content data over the distributed computing network, an evidential gathering of facts in rebuttal of the sentiment expression, the evidential gathering being directed to one or more assertions associated with the sentiment expression. ### Claim 12 (depends on 11) The server computing system of claim 11 wherein the social media content comprises one or more of: a hashtag, a twitter handle, an emoticon, at least a portion of a website content, a text string produced via a speech to text conversion of at least a portion of an audio file, a message exchange, an image, and at least a video portion. ### Claim 13 (depends on 12) The server computing system of claim 12 wherein the plurality of subjects of interest comprises one or more of a named product, a named feature, a named brand, a named entity, a named individual, and a named organizational group. ### Claim 14 (depends on 11) The server computing system of claim 11 wherein the sentiment score is determined based on (i) a sentiment score in accordance with the sentiment intensity rating and (ii) an engagement score. ### Claim 15 (depends on 14) The server computing system of claim 14 wherein the sentiment score is determined in accordance with a trained neural network machine learning model in conjunction with the social media content. ### Claim 16 (depends on 14) The server computing system of claim 14 wherein the first and at least a second portions of the sentiment score that is attributable to the first and the at least a second subjects of interest respectively are determined based respective sentiment scores and engagement scores. ### Claim 17 (depends on 16) The server computing system of claim 16 wherein at least one of the first and the at least a second engagement actions are generated upon reaching at least one of: (i) a predetermined threshold of the sentiment score; (ii) a rate of growth of the transient sentiment community that receives the content and the sentiment expression; (iii) respective predetermined sentiment attribution thresholds associated with the first and at least a second portions; and (iv) a rate of growth of the NSS over at least a period of time. ### Claim 18 (depends on 16) The server computing system of claim 16 wherein generating at least one of the first and at least a second engagement actions comprises: accessing, by the processor of the computing system, a fact check engine; receiving a fact check result for at least one of the first and the at least second of the subjects of interest from the fact check engine in accordance with the sentiment expressive usage; and transmitting, to the community that receives the social media content data over the distributed computing network, the rebuttal of the sentiment expression based at least in part on the fact check result. ### Claim 19 (depends on 18) The server computing system of claim 18 further including instructions executable in the processor to cause operations comprising: identifying one or more sources of dissemination of one or more assertions associated with at least one of the first and the at least a second subjects of interest; and retaining, as potential evidence in a reputation based legal or administrative proceeding, time stamped information associated with the one or more sources, at least some portions of the social media content, and the fact check results. ### Claim 20 A non-transitory computer readable medium storing instructions, the instructions being executable in a processor, the instructions when executed in the processor causing the processor to implement operations comprising: detecting, based at least in part upon a semantic similarity analysis performed in a processor of the computing system, content associated with a plurality of subjects of interest, the content defined in accordance with at least one text character string that is included within social media content data received at the computing system, the content including a sentiment expression associated with the plurality of subjects of interest, the sentiment expression being characterized in accordance with at least one sentiment parameter associated with a sentiment score (NSS); identifying, based on continuously monitoring, by the processor, a first and at least a second subjects of interest of the plurality upon accessing, by the processor, a sentiment identification component stored in a memory of the computing system and a sentiment intensity rating associated with the at least one sentiment parameter in accordance with sentiment expression; determining, responsive to identifying the first and at least a second subjects of interest, a first and at least a second portions of the sentiment score that is attributable to the first and the at least a second subjects of interest respectively; and triggering, based on transmission to a community that receives the social media content data over the distributed computing network, an evidential gathering of facts in rebuttal of the sentiment expression, the evidential gathering being directed to one or more assertions associated with the sentiment expression.