Using knowledge graphs to explain entity co-occurrence in Twitter

Yiwei Wang, Mark James Carman, Yuan Fang Li

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

    Abstract

    Modern Knowledge Graphs such as DBPedia contain significant information regarding Named Entities and the logical relationships which exist between them. Twitter on the other hand, contains important information on the popularity and frequency with which these entities are mentioned and discussed in combination with one another. In this paper we investigate whether these two sources of information can be used to complement and explain one another. In particular, we would like to know whether the logical relationships (a.k.a. semantic paths) which exist between pairs of known entities can help to explain the frequency with which those entities co-occur with one another in Twitter. To do this we train attranking function over semantic paths between pairs of entities. The aim of the ranker is to identify the path that most likely explains why a particular pair of entities have appeared together in a particular tweet. We train the ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrate the efficacy of the model for determining why pairs of entities occur together in tweets.

    LanguageEnglish
    Title of host publicationCIKM'17
    Subtitle of host publicationProceedings of the 2017 ACM Conference on Information and Knowledge Management
    EditorsMark Sanderson, Ada Fu, Jimeng Sun, Shane Culpepper, Eric Lo, Joyce Ho, Debora Donato, Rakesh Agrawal, Yu Zheng, Carlos Castillo, Aixin Sun, Vincent S. Tseng, Chenliang Li
    Place of PublicationNew York NY USA
    PublisherAssociation for Computing Machinery (ACM)
    Pages2351-2354
    Number of pages4
    ISBN (Print)9781450349185
    DOIs
    Publication statusPublished - 6 Nov 2017
    EventACM International Conference on Information and Knowledge Management 2017 - Singapore, Singapore
    Duration: 6 Nov 201710 Nov 2017
    Conference number: 26th
    http://www.cikmconference.org/CIKM2017/

    Conference

    ConferenceACM International Conference on Information and Knowledge Management 2017
    Abbreviated titleCIKM 2017
    CountrySingapore
    CitySingapore
    Period6/11/1710/11/17
    Internet address

    Keywords

    • DBPedia
    • Importance ranking
    • Information retrieval
    • Knowledge graphs
    • Machine learning
    • Microblog
    • Twitter

    Cite this

    Wang, Y., Carman, M. J., & Li, Y. F. (2017). Using knowledge graphs to explain entity co-occurrence in Twitter. In M. Sanderson, A. Fu, J. Sun, S. Culpepper, E. Lo, J. Ho, D. Donato, R. Agrawal, Y. Zheng, C. Castillo, A. Sun, V. S. Tseng, ... C. Li (Eds.), CIKM'17: Proceedings of the 2017 ACM Conference on Information and Knowledge Management (pp. 2351-2354). New York NY USA: Association for Computing Machinery (ACM). https://doi.org/10.1145/3132847.3133161
    Wang, Yiwei ; Carman, Mark James ; Li, Yuan Fang. / Using knowledge graphs to explain entity co-occurrence in Twitter. CIKM'17: Proceedings of the 2017 ACM Conference on Information and Knowledge Management. editor / Mark Sanderson ; Ada Fu ; Jimeng Sun ; Shane Culpepper ; Eric Lo ; Joyce Ho ; Debora Donato ; Rakesh Agrawal ; Yu Zheng ; Carlos Castillo ; Aixin Sun ; Vincent S. Tseng ; Chenliang Li. New York NY USA : Association for Computing Machinery (ACM), 2017. pp. 2351-2354
    @inproceedings{a48b9b5342f54194afcfcb6c3002eebf,
    title = "Using knowledge graphs to explain entity co-occurrence in Twitter",
    abstract = "Modern Knowledge Graphs such as DBPedia contain significant information regarding Named Entities and the logical relationships which exist between them. Twitter on the other hand, contains important information on the popularity and frequency with which these entities are mentioned and discussed in combination with one another. In this paper we investigate whether these two sources of information can be used to complement and explain one another. In particular, we would like to know whether the logical relationships (a.k.a. semantic paths) which exist between pairs of known entities can help to explain the frequency with which those entities co-occur with one another in Twitter. To do this we train attranking function over semantic paths between pairs of entities. The aim of the ranker is to identify the path that most likely explains why a particular pair of entities have appeared together in a particular tweet. We train the ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrate the efficacy of the model for determining why pairs of entities occur together in tweets.",
    keywords = "DBPedia, Importance ranking, Information retrieval, Knowledge graphs, Machine learning, Microblog, Twitter",
    author = "Yiwei Wang and Carman, {Mark James} and Li, {Yuan Fang}",
    year = "2017",
    month = "11",
    day = "6",
    doi = "10.1145/3132847.3133161",
    language = "English",
    isbn = "9781450349185",
    pages = "2351--2354",
    editor = "Mark Sanderson and Ada Fu and Jimeng Sun and Shane Culpepper and Eric Lo and Joyce Ho and Debora Donato and Rakesh Agrawal and Yu Zheng and Carlos Castillo and Aixin Sun and Tseng, {Vincent S.} and Chenliang Li",
    booktitle = "CIKM'17",
    publisher = "Association for Computing Machinery (ACM)",
    address = "United States",

    }

    Wang, Y, Carman, MJ & Li, YF 2017, Using knowledge graphs to explain entity co-occurrence in Twitter. in M Sanderson, A Fu, J Sun, S Culpepper, E Lo, J Ho, D Donato, R Agrawal, Y Zheng, C Castillo, A Sun, VS Tseng & C Li (eds), CIKM'17: Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Association for Computing Machinery (ACM), New York NY USA, pp. 2351-2354, ACM International Conference on Information and Knowledge Management 2017, Singapore, Singapore, 6/11/17. https://doi.org/10.1145/3132847.3133161

    Using knowledge graphs to explain entity co-occurrence in Twitter. / Wang, Yiwei; Carman, Mark James; Li, Yuan Fang.

    CIKM'17: Proceedings of the 2017 ACM Conference on Information and Knowledge Management. ed. / Mark Sanderson; Ada Fu; Jimeng Sun; Shane Culpepper; Eric Lo; Joyce Ho; Debora Donato; Rakesh Agrawal; Yu Zheng; Carlos Castillo; Aixin Sun; Vincent S. Tseng; Chenliang Li. New York NY USA : Association for Computing Machinery (ACM), 2017. p. 2351-2354.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

    TY - GEN

    T1 - Using knowledge graphs to explain entity co-occurrence in Twitter

    AU - Wang, Yiwei

    AU - Carman, Mark James

    AU - Li, Yuan Fang

    PY - 2017/11/6

    Y1 - 2017/11/6

    N2 - Modern Knowledge Graphs such as DBPedia contain significant information regarding Named Entities and the logical relationships which exist between them. Twitter on the other hand, contains important information on the popularity and frequency with which these entities are mentioned and discussed in combination with one another. In this paper we investigate whether these two sources of information can be used to complement and explain one another. In particular, we would like to know whether the logical relationships (a.k.a. semantic paths) which exist between pairs of known entities can help to explain the frequency with which those entities co-occur with one another in Twitter. To do this we train attranking function over semantic paths between pairs of entities. The aim of the ranker is to identify the path that most likely explains why a particular pair of entities have appeared together in a particular tweet. We train the ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrate the efficacy of the model for determining why pairs of entities occur together in tweets.

    AB - Modern Knowledge Graphs such as DBPedia contain significant information regarding Named Entities and the logical relationships which exist between them. Twitter on the other hand, contains important information on the popularity and frequency with which these entities are mentioned and discussed in combination with one another. In this paper we investigate whether these two sources of information can be used to complement and explain one another. In particular, we would like to know whether the logical relationships (a.k.a. semantic paths) which exist between pairs of known entities can help to explain the frequency with which those entities co-occur with one another in Twitter. To do this we train attranking function over semantic paths between pairs of entities. The aim of the ranker is to identify the path that most likely explains why a particular pair of entities have appeared together in a particular tweet. We train the ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrate the efficacy of the model for determining why pairs of entities occur together in tweets.

    KW - DBPedia

    KW - Importance ranking

    KW - Information retrieval

    KW - Knowledge graphs

    KW - Machine learning

    KW - Microblog

    KW - Twitter

    UR - http://www.scopus.com/inward/record.url?scp=85037341536&partnerID=8YFLogxK

    U2 - 10.1145/3132847.3133161

    DO - 10.1145/3132847.3133161

    M3 - Conference Paper

    SN - 9781450349185

    SP - 2351

    EP - 2354

    BT - CIKM'17

    A2 - Sanderson, Mark

    A2 - Fu, Ada

    A2 - Sun, Jimeng

    A2 - Culpepper, Shane

    A2 - Lo, Eric

    A2 - Ho, Joyce

    A2 - Donato, Debora

    A2 - Agrawal, Rakesh

    A2 - Zheng, Yu

    A2 - Castillo, Carlos

    A2 - Sun, Aixin

    A2 - Tseng, Vincent S.

    A2 - Li, Chenliang

    PB - Association for Computing Machinery (ACM)

    CY - New York NY USA

    ER -

    Wang Y, Carman MJ, Li YF. Using knowledge graphs to explain entity co-occurrence in Twitter. In Sanderson M, Fu A, Sun J, Culpepper S, Lo E, Ho J, Donato D, Agrawal R, Zheng Y, Castillo C, Sun A, Tseng VS, Li C, editors, CIKM'17: Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York NY USA: Association for Computing Machinery (ACM). 2017. p. 2351-2354 https://doi.org/10.1145/3132847.3133161