# US 10,375,005 B2 · Dynamic hashtag ordering based on projected interest > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,375,005 B2 - Document ID: US10375005B2 - Status: Granted - Kind: B2 - Application number: 15/406,352 - Filed: 2017-01-13 - Published: 2018-07-19 - Granted: 2019-08-06 - Earliest claimed: 2017-01-13 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Kelley L. Anders; Jonathan Dunne; Robert H. Grant; Trudy L. Hewitt - Web page: https://patentgrep.com/patent/US10375005B2 ## CPC - H04L 51/52: for supporting social networking services - H04L 51/216: Handling conversation history, e.g. grouping of messages in sessions or threads - H04L 67/306: User profiles - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A method, computer program product, and system includes a processor(s) obtaining a hashtag and analyzing the hashtag to identify components comprising the hashtag. The processor(s) generate sub-hashtags, where each of the sub-hashtags includes at least one component. The processor(s) obtain, over an Internet connection, via a user interface of a social media platform displayed on a first computing resource, an entry by a user comprising text and the hashtag. The processor(s) obtains from a second computing resource, a request from a second user to access the entry that includes parameters of the second user on the platform. The processor(s) determine that a sub-hashtag is most relevant to the second user. The processor(s) configure instructions to display a customized entry, where the customized entry includes the text and the relevant sub-hashtag for the second user. The processor(s) instruct the second computing resource to display the customized entry in its user interface. ## Claims ### Claim 1 A computer-implemented method, comprising: obtaining, by one or more processors, over a communications connection, a hashtag; identifying, by the one or more processors, at least two linguistic components comprising the hashtag, wherein the identifying the at least two linguistic components comprises executing a natural language processing algorithm of a text string comprising the hashtag; generating, by the one or more processors, at least two sub-hashtags, wherein each of the at least two sub-hashtags comprises at least one linguistic component of the at least two linguistic components; obtaining, by the one or more processors, over an Internet connection, via a user interface of a social media platform displayed on a first computing resource, an entry by a user comprising text and the hashtag; obtaining, by the one or more processors, over the Internet connection, from a second computing resource accessing the social media platform, a request from a second user to access the entry, wherein the request comprises parameters of a profile of the second user on the social media platform; determining, by the one or more processors, that a sub-hashtag of the at least two sub-hashtags is most relevant to a third user, wherein the determining comprises: inferring relationships between the parameters of the profile of the third user and the at least two linguistic components, and selecting the sub-hashtag associated with a more significant relationship of the inferred relationships; configuring, by the one or more processor, instructions to display a customized entry, wherein the customized entry comprises the text and the relevant sub-hashtag for the second user; and instructing, by the one or more processors, over the Internet connection, based on the instructions, the second computing resource to display the customized entry in the user interface of the second computing resource. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein based on receiving the instructing, the second computing resource displays the customized entry in the user interface of the second computing resource. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the hashtag comprises a text string and the least two linguistic components each comprise a portion of the text string. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein at least two linguistic components of the least two linguistic components comprise a common portion of the text string. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, the natural language processing selected from the group consisting of: artificial intelligence and computational linguistics. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the generating at least two sub-hashtags comprises executing a principal component analysis to determine a related set of concepts based on the at least two linguistic components to generate sub-hashtags from the hashtag. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, further comprising: obtaining, by the one or more processors, over the Internet connection, from a third computing resource accessing the social media platform, a request from a third user to access the entry, wherein the request comprises parameters of a profile of the third user on the social media platform; determining, by the one or more processors, that a sub-hashtag of the at least two sub-hashtags is most relevant to the third user, wherein the determining comprises: inferring relationships between the parameters of the profile of the third user and the at least two linguistic components, and selecting the sub-hashtag associated with a more significant relationship of the inferred relationships; configuring, by the one or more processor, instructions to display a customized entry for the third user, wherein the customized entry for the third user comprises the text and the relevant sub-hashtag for the third user; and instructing, by the one or more processors, over the Internet connection, based on the instructions, the second computing resource to display the customized entry for the third user in the user interface of the third computing resource. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, wherein based on receiving the instructing, the third computing resource displays the customized entry in the user interface of the third computing resource. ### Claim 9 (depends on 7) The computer-implemented method of claim 7, wherein the relevant sub-hashtag for the second user and the relevant sub-hashtag for the third user comprise a common sub-hashtag of the at least two hashtags. ### Claim 10 (depends on 8) The computer-implemented method of claim 8, wherein the relevant sub-hashtag for the second user and the relevant sub-hashtag for the third user comprise different sub-hashtags of the at least two hashtags. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, wherein the determining that a sub-hashtag of the at least two sub-hashtags is most relevant to the second user further comprises identifying the second user. ### Claim 12 (depends on 1) The computer-implemented method of claim 1, the parameters of the profile comprises historical entries of the second user on the social media platform during a pre-defined period of time. ### Claim 13 (depends on 1) The computer-implemented method of claim 1, further comprising: identifying, by the one or more processors, historical entries by the second user on the social media platform with historical hashtags similar to the hashtag; and updating, by the one or more processors, the historical hashtags to the sub-hashtag, wherein a subsequent user accessing an entry of the historical entries views the sub-hashtag. ### Claim 14 (depends on 13) The computer-implemented method of claim 13, wherein the updating the historical hashtags comprises replacing each of the historical hashtags with the sub-hashtag. ### Claim 15 A computer program product comprising: a computer readable storage medium readable by one or more processors and storing instructions for execution by the one or more processors for performing a method comprising: obtaining, by the one or more processors, over a communications connection, a hashtag; identifying, by the one or more processors, at least two linguistic components comprising the hashtag, wherein the identifying the at least two linguistic components comprises executing a natural language processing algorithm of a text string comprising the hashtag; generating, by the one or more processors, at least two sub-hashtags, wherein each of the at least two sub-hashtags comprises at least one linguistic component of the at least two linguistic components; obtaining, by the one or more processors, over an Internet connection, via a user interface of a social media platform displayed on a first computing resource, an entry by a user comprising text and the hashtag; obtaining, by the one or more processors, over the Internet connection, from a second computing resource accessing the social media platform, a request from a second user to access the entry, wherein the request comprises parameters of a profile of the second user on the social media platform; determining, by the one or more processors, that a sub-hashtag of the at least two sub-hashtags is most relevant to a third user, wherein the determining comprises: inferring relationships between the parameters of the profile of the third user and the at least two linguistic components, and selecting the sub-hashtag associated with a more significant relationship of the inferred relationships; configuring, by the one or more processor, instructions to display a customized entry, wherein the customized entry comprises the text and the relevant sub-hashtag for the second user; and instructing, by the one or more processors, over the Internet connection, based on the instructions, the second computing resource to display the customized entry in the user interface of the second computing resource. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein the hashtag comprises a text string and the least two linguistic components each comprise a portion of the text string. ### Claim 17 (depends on 16) The computer program product of claim 16, wherein at least two linguistic components of the least two linguistic components comprise a common portion of the text string. ### Claim 18 A system comprising: a memory; one or more processors in communication with the memory; and program instructions executable by the one or more processors via the memory to perform a method, the method comprising: obtaining, by the one or more processors, over a communications connection, a hashtag; identifying, by the one or more processors, at least two linguistic components comprising the hashtag, wherein the identifying the at least two linguistic components comprises executing a natural language processing algorithm of a text string comprising the hashtag; generating, by the one or more processors, at least two sub-hashtags, wherein each of the at least two sub-hashtags comprises at least one linguistic component of the at least two linguistic components; obtaining, by the one or more processors, over an Internet connection, via a user interface of a social media platform displayed on a first computing resource, an entry by a user comprising text and the hashtag; obtaining, by the one or more processors, over the Internet connection, from a second computing resource accessing the social media platform, a request from a second user to access the entry, wherein the request comprises parameters of a profile of the second user on the social media platform; determining, by the one or more processors, that a sub-hashtag of the at least two sub-hashtags is most relevant to a third user, wherein the determining comprises: inferring relationships between the parameters of the profile of the third user and the at least two linguistic components, and selecting the sub-hashtag associated with a more significant relationship of the inferred relationships; configuring, by the one or more processor, instructions to display a customized entry, wherein the customized entry comprises the text and the relevant sub-hashtag for the second user; and instructing, by the one or more processors, over the Internet connection, based on the instructions, the second computing resource to display the customized entry in the user interface of the second computing resource.