# US 2018/0025069 A1 · Method and system for detecting personal life events of users > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0025069 A1 - Document ID: US20180025069A1 - Status: Published application - Kind: A1 - Application number: 15/215,684 - Filed: 2016-07-21 - Published: 2018-01-25 - Earliest claimed: 2016-07-21 - Assignees: Xerox Corporation - Applicants: Xerox Corporation - Inventors: Saurabh Kataria - Web page: https://patentgrep.com/patent/US20180025069A1 ## CPC - G06F 40/169: Annotation, e.g. comment data or footnotes - G06F 16/24573: {using data annotations, e.g. user-defined metadata} - G06F 16/285: {Clustering or classification} - G06N 20/00: Machine learning - G06Q 10/40: Business processes related to social networking or social networking services - H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - 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 - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract The disclosed embodiments illustrate methods and systems for detecting personal life events of users. The method includes training classifiers based on a set of features extracted from each of an annotated first set of social media data. The first set of social media is associated with one or more first categories. Further, the first set of social media data are annotated by one or more crowdworkers based on one or more second categories. The method further includes extracting a second set of social media data of one or more users, associated with the one or more first categories, from the one or more social media platforms. The method further includes categorizing the extracted second set of social media data into the one or more second categories by use of the trained classifiers. The categorization is further utilized to detect the personal life events of the one or more users. ## Claims ### Claim 1 A method for detecting personal life events of users by a computing server, the method comprising: extracting, by a data extraction processor at the computing server, a first set of social media data, associated with one or more first categories, from one or more social media platforms over a communication network; transmitting, by a transceiver at the computing server, the extracted first set of social media data to one or more crowdworkers over a crowdsourcing platform for annotating the extracted first set of social media data based on one or more second categories; extracting, by a feature extraction processor at the computing server, a set of features from each of the annotated first set of social media data, wherein the extracted set of features includes at least a set of dialogue features that is indicative of at least one or more sentiments in the annotated first set of social media data; training, by a processor at the computing server, one or more first classifiers based on the extracted set of features associated with each of the annotated first set of social media data; extracting, by the data extraction processor, a second set of social media data of one or more users, associated with the one or more first categories, from the one or more social media platforms over the communication network; and categorizing, by the processor, the extracted second set of social media data into the one or more second categories by use of the trained one or more first classifiers, wherein the categorization is utilized to detect the personal life events of the one or more users. ### Claim 2 (depends on 1) The method of claim 1, wherein the first set of social media data is extracted, by the data extraction processor, based on one or more keywords associated with the one or more first categories, and wherein the extracted first set of social media data corresponds to a predefined time period. ### Claim 3 (depends on 1) The method of claim 1, wherein the extracted first set of social media data further comprises a set of surrounding data and a set of conversation data associated with each of the first set of social media data. ### Claim 4 (depends on 1) The method of claim 1, wherein the one or more first categories are based on at least one or more personal events, social events, and/or professional events. ### Claim 5 (depends on 1) The method of claim 1, wherein the transmitted first set of social media data further comprises one or more data samples associated with each of the one or more second categories, wherein the one or more second categories correspond to a self-associated event category, other-associated event category, or a generically-associated event category. ### Claim 6 (depends on 1) The method of claim 1 further comprising receiving, by the transceiver, the annotated first set of social media data from the one or more crowdworkers over the crowdsourcing platform. ### Claim 7 (depends on 1) The method of claim 1, wherein the set of features further comprises a set of language features, a set of Part-of-Speech (POS) features, a set of dependency features, and a set of mention features. ### Claim 8 (depends on 7) The method of claim 7, wherein each of the set of language features corresponds to an n-gram feature vector generated from each of the annotated first set of social media data. ### Claim 9 (depends on 7) The method of claim 7, wherein each of the set of POS features corresponds to an n-gram POS vectors generated from each of the annotated first set of social media data. ### Claim 10 (depends on 7) The method of claim 7, wherein each of the set of dependency features is based on at least a dependency relationship between at least a plurality words in the annotated first set of social media data. ### Claim 11 (depends on 7) The method of claim 7, wherein each of the set of mention features is based on at least a mention of demographic attributes of the one or more users in the annotated first set of social media data. ### Claim 12 (depends on 1) The method of claim 1 further comprising determining the set of dialogue features, the method comprising: segregating, by the processor, the annotated first set of social media data into a first portion of annotated first set of social media data and a second portion of annotated first set of social media data; transmitting, by the transceiver, the first portion of annotated first set of social media data to the one or more crowdworkers over the crowdsourcing platform for identifying the one or more sentiments in each of the first portion of annotated first set of social media data; receiving, by the transceiver, the identified one or more sentiments in the first portion of annotated first set of social media data from the one or more crowdworkers over the crowdsourcing platform; training, by the processor, one or more second classifiers based on the identified one or more sentiments in the first portion of annotated first set of social media data; and determining, by the processor, the one or more sentiments in the second portion of annotated first set of social media data by use of the trained one or more second classifiers. ### Claim 13 (depends on 1) The method of claim 1 further comprising rendering, by the processor, a recommendation of one or more products/services on a user interface displayed on a display screen of a computing device associated with each of the one or more users, based on at least the detected personal life events of the one or more users. ### Claim 14 A system for detecting personal life events of users, the system comprising: one or more processors configured to: extract a first set of social media data, associated with one or more first categories, from one or more social media platforms over a communication network; transmit the extracted first set of social media data to one or more crowdworkers over a crowdsourcing platform for annotating the extracted first set of social media data based on one or more second categories; extract a set of features from each of the annotated first set of social media data, wherein the extracted set of features includes at least a set of dialogue features that is indicative of at least one or more sentiments in the annotated first set of social media data; train one or more first classifiers based on the extracted set of features associated with each of the annotated first set of social media data; extract a second set of social media data of one or more users, associated with the one or more first categories, from the one or more social media platforms over the communication network; and categorize the extracted second set of social media data into the one or more second categories by use of the trained one or more first classifiers, wherein the categorization is utilized to detect the personal life events of the one or more users. ### Claim 15 (depends on 14) The system of claim 14, wherein the one or more first categories are based on at least one or more personal events, social events, and/or professional events. ### Claim 16 (depends on 14) The system of claim 14, wherein the transmitted first set of social media data further comprises one or more data samples associated with each of the one or more second categories, wherein the one or more second categories correspond to a self-associated event category, other-associated event category, or a generically-associated event category. ### Claim 17 (depends on 14) The system of claim 14, wherein the one or more processors are further configured to receive the annotated first set of social media data from the one or more crowdworkers over the crowdsourcing platform. ### Claim 18 (depends on 14) The system of claim 14, wherein the set of features further comprises a set of language features, a set of Part-of-Speech (POS) features, a set of dependency features, and a set of mention features. ### Claim 19 (depends on 14) The system of claim 14, wherein the one or more processors are further configured to render a recommendation of one or more products/services on a user interface displayed on a display screen of a computing device associated with each of the one or more users, based on at least the detected personal life events of the one or more users. ### Claim 20 A computer program product for use with a computer, the computer program product comprising a non-transitory computer readable medium, wherein the non-transitory computer readable medium stores a computer program code detecting personal life events of users, wherein the computer program code is executable by one or more processors to: extract a first set of social media data, associated with one or more first categories, from one or more social media platforms over a communication network; transmit the extracted first set of social media data to one or more crowdworkers over a crowdsourcing platform for annotating the extracted first set of social media data based on one or more second categories; extract a set of features from each of the annotated first set of social media data, wherein the extracted set of features includes at least a set of dialogue features that is indicative of at least one or more sentiments in the annotated first set of social media data; train one or more first classifiers based on the extracted set of features associated with each of the annotated first set of social media data; extract a second set of social media data of one or more users, associated with the one or more first categories, from the one or more social media platforms over the communication network; and categorize the extracted second set of social media data into the one or more second categories by use of the trained one or more first classifiers, wherein the categorization is utilized to detect the personal life events of the one or more users.