Using rhetorical structure in sentiment analysis

Alexander Hogenboom, Flavius Frasincar, Franciska M.G. de Jong, Uzay Kaymak

    Research output: Contribution to journalArticleAcademicpeer-review

    28 Citations (Scopus)

    Abstract

    Automated sentiment analysis has become an active field of study with a broad applicability. One of the key open research issues lies in dealing with structural aspects of text when analyzing its conveyed sentiment. Recent work uses structural aspects of text in order to distinguish important text segments from less important ones in terms of their contribution to the overall sentiment. Yet, existing methods are conned to making coarse-grained distinctions between text segments based on segments' rhetorical roles, while not accounting for the full hierarchical rhetorical structure in which these roles are dened. We hypothesize that a better understanding of a text's conveyed sentiment can be obtained by guiding automated sentiment analysis by the full rhetorical structure of text. We evaluate our hypothesis in a framework for sentiment analysis that is based on Rhetorical Structure Theory, at the level of sentences, paragraphs, and documents. On an English movie review corpus, we obtain signicant classication performance improvements compared to baselines not or only shallowly accounting for rhetorical structure, with the best results generated by exploiting a text's full sentential rhetorical structure.
    Original languageUndefined
    Pages (from-to)69-77
    Number of pages9
    JournalCommunications of the ACM
    Volume58
    Issue number7
    DOIs
    Publication statusPublished - Jul 2015

    Keywords

    • EWI-25974
    • METIS-312579
    • IR-96334

    Cite this

    Hogenboom, Alexander ; Frasincar, Flavius ; de Jong, Franciska M.G. ; Kaymak, Uzay. / Using rhetorical structure in sentiment analysis. In: Communications of the ACM. 2015 ; Vol. 58, No. 7. pp. 69-77.
    @article{3324ecf532814c3f877cc6dd5b2ebead,
    title = "Using rhetorical structure in sentiment analysis",
    abstract = "Automated sentiment analysis has become an active field of study with a broad applicability. One of the key open research issues lies in dealing with structural aspects of text when analyzing its conveyed sentiment. Recent work uses structural aspects of text in order to distinguish important text segments from less important ones in terms of their contribution to the overall sentiment. Yet, existing methods are conned to making coarse-grained distinctions between text segments based on segments' rhetorical roles, while not accounting for the full hierarchical rhetorical structure in which these roles are dened. We hypothesize that a better understanding of a text's conveyed sentiment can be obtained by guiding automated sentiment analysis by the full rhetorical structure of text. We evaluate our hypothesis in a framework for sentiment analysis that is based on Rhetorical Structure Theory, at the level of sentences, paragraphs, and documents. On an English movie review corpus, we obtain signicant classication performance improvements compared to baselines not or only shallowly accounting for rhetorical structure, with the best results generated by exploiting a text's full sentential rhetorical structure.",
    keywords = "EWI-25974, METIS-312579, IR-96334",
    author = "Alexander Hogenboom and Flavius Frasincar and {de Jong}, {Franciska M.G.} and Uzay Kaymak",
    year = "2015",
    month = "7",
    doi = "10.1145/2699418",
    language = "Undefined",
    volume = "58",
    pages = "69--77",
    journal = "Communications of the ACM",
    issn = "0001-0782",
    publisher = "Association for Computing Machinery (ACM)",
    number = "7",

    }

    Using rhetorical structure in sentiment analysis. / Hogenboom, Alexander; Frasincar, Flavius; de Jong, Franciska M.G.; Kaymak, Uzay.

    In: Communications of the ACM, Vol. 58, No. 7, 07.2015, p. 69-77.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Using rhetorical structure in sentiment analysis

    AU - Hogenboom, Alexander

    AU - Frasincar, Flavius

    AU - de Jong, Franciska M.G.

    AU - Kaymak, Uzay

    PY - 2015/7

    Y1 - 2015/7

    N2 - Automated sentiment analysis has become an active field of study with a broad applicability. One of the key open research issues lies in dealing with structural aspects of text when analyzing its conveyed sentiment. Recent work uses structural aspects of text in order to distinguish important text segments from less important ones in terms of their contribution to the overall sentiment. Yet, existing methods are conned to making coarse-grained distinctions between text segments based on segments' rhetorical roles, while not accounting for the full hierarchical rhetorical structure in which these roles are dened. We hypothesize that a better understanding of a text's conveyed sentiment can be obtained by guiding automated sentiment analysis by the full rhetorical structure of text. We evaluate our hypothesis in a framework for sentiment analysis that is based on Rhetorical Structure Theory, at the level of sentences, paragraphs, and documents. On an English movie review corpus, we obtain signicant classication performance improvements compared to baselines not or only shallowly accounting for rhetorical structure, with the best results generated by exploiting a text's full sentential rhetorical structure.

    AB - Automated sentiment analysis has become an active field of study with a broad applicability. One of the key open research issues lies in dealing with structural aspects of text when analyzing its conveyed sentiment. Recent work uses structural aspects of text in order to distinguish important text segments from less important ones in terms of their contribution to the overall sentiment. Yet, existing methods are conned to making coarse-grained distinctions between text segments based on segments' rhetorical roles, while not accounting for the full hierarchical rhetorical structure in which these roles are dened. We hypothesize that a better understanding of a text's conveyed sentiment can be obtained by guiding automated sentiment analysis by the full rhetorical structure of text. We evaluate our hypothesis in a framework for sentiment analysis that is based on Rhetorical Structure Theory, at the level of sentences, paragraphs, and documents. On an English movie review corpus, we obtain signicant classication performance improvements compared to baselines not or only shallowly accounting for rhetorical structure, with the best results generated by exploiting a text's full sentential rhetorical structure.

    KW - EWI-25974

    KW - METIS-312579

    KW - IR-96334

    U2 - 10.1145/2699418

    DO - 10.1145/2699418

    M3 - Article

    VL - 58

    SP - 69

    EP - 77

    JO - Communications of the ACM

    JF - Communications of the ACM

    SN - 0001-0782

    IS - 7

    ER -