# US 2020/0401639 A1 · Personalizing a search query using social media > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401639 A1 - Document ID: US20200401639A1 - Status: Published application - Kind: A1 - Application number: 16/445,258 - Filed: 2019-06-19 - Published: 2020-12-24 - Earliest claimed: 2019-06-19 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Timo Kussmaul; Uwe K. Hansmann; Kai Brennenstuhl; Andreas Prokoph; Thomas Steinheber - Web page: https://patentgrep.com/patent/US20200401639A1 ## CPC - G06F 16/9536: Search customisation based on social or collaborative filtering - G06F 40/295: Named entity recognition - G06F 16/328: {Management therefor} - G06F 16/3329: Natural language query formulation - G06F 16/3349: Reuse of stored results of previous queries - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The invention relates to a method for personalizing a search of a search service. The search service comprises a search index with content items of a search type being used as first search results for first search queries issued by the client application and providing second search queries to be executed for retrieving second search results to be returned in reply to the first search queries. The method comprises using social media content items retrieved from social media services for extracting a set of keywords comprised by the social media content items. A second search query modified, wherein the modifying comprises adding keywords of the set keywords as additional search parameters of the determined second search query. ## Claims ### Claim 1 A method for personalizing a search of a search service comprising: retrieving, by one or more computer processors, one or more social media content items from the one or more social media services by a personalization component; forwarding, by one or more computer processors, the retrieved social media content items by the personalization component to a content analyzing service configured for extracting keywords from the social media content items; receiving, by one or more computer processors, by the personalization component a set of one or more keywords extracted from the social media content items from the content analyzing service; determining, by one or more computer processors, a content item of a search query type comprising a second search query to be modified using the set of keywords; modifying, by one or more computer processors, the determined second search query, wherein the modifying comprises adding one or more keywords of the set keywords as additional search parameters of the determined second search query; and storing, by one or more computer processors, the modified second search query as a content item of the search query type in a search index of the search service. ### Claim 2 (depends on 1) The method of claim 1, wherein the search service and the personalization component are provided by a content management system, wherein the content management system further provides an authoring service which enables creating and editing content items managed by the content management system, wherein the authoring service is used for modifying of the determined second search query. ### Claim 3 (depends on 2) The method of claim 2, wherein the content management system further comprises the content analyzing service. ### Claim 4 (depends on 1) The method of claim 1, wherein the content analyzing service uses a concept extraction method for extracting the set of keywords, wherein the set of keywords represents characteristic semantic aspects of the retrieved social media content items. ### Claim 5 (depends on 1) The method of claim 1, wherein the content analyzing service uses an image tagging method for extracting the set of keywords. ### Claim 6 (depends on 1) The method of claim 1, wherein the content analyzing service uses a label extraction method for extracting the set of keywords. ### Claim 7 (depends on 1) The method of claim 1, wherein the content analyzing service uses a topic extraction method for extracting the set of keywords. ### Claim 8 (depends on 1) The method of claim 1, wherein the content analyzing service uses a tone analysis method for extracting the set of keywords. ### Claim 9 (depends on 1) The method of claim 1, wherein the content analyzing service uses personality insights for extracting the set of keywords. ### Claim 10 (depends on 1) The method of claim 1, wherein the content analyzing service uses a named-entity recognition method for extracting the set of keywords. ### Claim 11 (depends on 1) The method of claim 1, wherein the retrieved one or more social media content items relate to one or more social media activities of a user of a client application. ### Claim 12 (depends on 11) The method of claim 11, wherein the retrieved one or more social media content items are a subset of social media content items related to social media activities selected using dates of the respective activities. ### Claim 13 (depends on 11) The method of claim 11, wherein the retrieved one or more social media content items are a subset of social media content items related to social media activities selected using numbers of positive ratings of the respective activities. ### Claim 14 (depends on 11) The method of claim 11, wherein the retrieved one or more social media content items are a subset of social media content items related to social media activities selected using a clustering of users of the social media services comprising the user of the client application and associations of each of the users to the selected social media activities, wherein for the clustering of users is a distance measure over an analysis of a social graph. ### Claim 15 (depends on 1) The method of claim 1, wherein the extracted keywords are added to the determined second search query in form of one or more boosting sub-queries comprising the additional search parameters. ### Claim 16 (depends on 15) The method of claim 15, wherein the additional search parameters comprised by the boosting sub-queries are assigned with boosting factors for boosting second search results matching the additional search parameters. ### Claim 17 (depends on 1) The method of claim 1, further comprises: a search service comprising a search engine and a search index, wherein the search index comprises content items of a search query type for use as first search results for first search queries received from a client application, wherein the content items of the search query type comprise second search queries for use by the search service to search for second search results to be returned to the client application as search results for the first search queries, wherein a personalization component is provided configured for retrieving one or more social media content items from one or more social media services. ### Claim 18 (depends on 1) The method of claim 1, further comprises: receiving, by one or more computer processors, by the search service a first search query issued by the client application; executing, by one or more computer processors, the received first search query by the search service; retrieving, by one or more computer processors, the stored content item of the search query type providing the modified second search query as a first search result for the received first search query; executing, by one or more computer processors, the modified second search query by the search service; retrieving, by one or more computer processors, a set of content items as a second search result for the modified second search query; and sending, by one or more computer processors, the second search result to the client application as a result of the received first search query. ### Claim 19 A computer program product for personalizing a search of a search service comprising: one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the stored program instructions comprising: program instructions to retrieve one or more social media content items from the one or more social media services by a personalization component; program instructions to forward the retrieved social media content items by the personalization component to a content analyzing service configured for extracting keywords from the social media content items; program instructions to receive by the personalization component a set of one or more keywords extracted from the social media content items from the content analyzing service; program instructions to determine a content item of the search query type comprising a second search query to be modified using the set of keywords; program instructions to modify the determined second search query, wherein the modifying comprises adding one or more keywords of the set keywords as additional search parameters of the determined second search query; and program instructions to store the modified second search query as a content item of the search query type in the search index of the search service. ### Claim 20 A computer system for personalizing a search of a search service comprising: one or more computer processors; one or more computer readable storage media; and program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the stored program instructions comprising: program instructions to retrieve one or more social media content items from the one or more social media services by a personalization component; program instructions to forward the retrieved social media content items by the personalization component to a content analyzing service configured for extracting keywords from the social media content items; program instructions to receive by the personalization component a set of one or more keywords extracted from the social media content items from the content analyzing service; program instructions to determine a content item of the search query type comprising a second search query to be modified using the set of keywords; program instructions to modify the determined second search query, wherein the modifying comprises adding one or more keywords of the set keywords as additional search parameters of the determined second search query; and program instructions to store the modified second search query as a content item of the search query type in the search index of the search service.