Predicting iPhone Sales from iPhone Tweets

Niels Buus Lassen, Rene Madsen, Ravi Vatrapu

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    24 Downloads (Pure)

    Abstract

    Recent research in the field of computational social science have shown how data resulting from the widespread adoption and use of social media channels such as twitter can be used to predict outcomes such as movie revenues, election winners, localized moods, and epidemic outbreaks. Underlying assumptions for this research stream on predictive analytics are that social media actions such as tweeting, liking, commenting and rating are proxies for user/consumer’s attention to a particular object/product and that the shared digital artefact that is persistent can create social influence. In this paper, we demonstrate how social media data from twitter can be used to predict the sales of iPhones. Based on a conceptual model of social data consisting of social graph (actors, actions, activities, and artefacts) and social text (topics, keywords, pronouns, and sentiments), we develop and evaluate a linear regression model that transforms iPhone tweets into a prediction of the quarterly iPhone sales with an average error close to the established prediction models from investment banks. This strong correlation between iPhone tweets and iPhone sales becomes marginally stronger after incorporating sentiments of tweets. We discuss the findings and conclude with implications for predictive analytics with big social data.
    Original languageEnglish
    Title of host publicationProceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014
    EditorsManfred Reichert, Stefanie Rinderle-Ma, Georg Grossmann
    Number of pages10
    Place of PublicationLos Alamitos, CA
    PublisherIEEE
    Publication date2014
    Pages81-90
    ISBN (Print)9781479954704
    DOIs
    Publication statusPublished - 2014
    EventThe 18th IEEE Enterprise Computing Conference. EDOC 2014: Utilizing Big Data for the Enterprise of the Future - Ulm, Germany
    Duration: 1 Sep 20145 Sep 2014
    Conference number: 18
    http://www.edoc2014.org/

    Conference

    ConferenceThe 18th IEEE Enterprise Computing Conference. EDOC 2014
    Number18
    CountryGermany
    CityUlm
    Period01/09/201405/09/2014
    Internet address
    SeriesInternational Enterprise Distributed Object Computing Conference. Proceedings
    Volume18
    ISSN1541-7719

    Cite this

    Lassen, N. B., Madsen, R., & Vatrapu, R. (2014). Predicting iPhone Sales from iPhone Tweets. In M. Reichert, S. Rinderle-Ma, & G. Grossmann (Eds.), Proceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014 (pp. 81-90). Los Alamitos, CA: IEEE. International Enterprise Distributed Object Computing Conference. Proceedings, Vol.. 18 https://doi.org/10.1109/EDOC.2014.20
    Lassen, Niels Buus ; Madsen, Rene ; Vatrapu, Ravi. / Predicting iPhone Sales from iPhone Tweets. Proceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014. editor / Manfred Reichert ; Stefanie Rinderle-Ma ; Georg Grossmann. Los Alamitos, CA : IEEE, 2014. pp. 81-90 (International Enterprise Distributed Object Computing Conference. Proceedings, Vol. 18).
    @inproceedings{f5ece677f14040348a23701969a57671,
    title = "Predicting iPhone Sales from iPhone Tweets",
    abstract = "Recent research in the field of computational social science have shown how data resulting from the widespread adoption and use of social media channels such as twitter can be used to predict outcomes such as movie revenues, election winners, localized moods, and epidemic outbreaks. Underlying assumptions for this research stream on predictive analytics are that social media actions such as tweeting, liking, commenting and rating are proxies for user/consumer’s attention to a particular object/product and that the shared digital artefact that is persistent can create social influence. In this paper, we demonstrate how social media data from twitter can be used to predict the sales of iPhones. Based on a conceptual model of social data consisting of social graph (actors, actions, activities, and artefacts) and social text (topics, keywords, pronouns, and sentiments), we develop and evaluate a linear regression model that transforms iPhone tweets into a prediction of the quarterly iPhone sales with an average error close to the established prediction models from investment banks. This strong correlation between iPhone tweets and iPhone sales becomes marginally stronger after incorporating sentiments of tweets. We discuss the findings and conclude with implications for predictive analytics with big social data.",
    keywords = "Data science, Computational social science, Social data analytics, Predictive analytics, iPhone sales, iPhone tweets, Twitter",
    author = "Lassen, {Niels Buus} and Rene Madsen and Ravi Vatrapu",
    year = "2014",
    doi = "10.1109/EDOC.2014.20",
    language = "English",
    isbn = "9781479954704",
    series = "International Enterprise Distributed Object Computing Conference. Proceedings",
    pages = "81--90",
    editor = "Manfred Reichert and Stefanie Rinderle-Ma and Georg Grossmann",
    booktitle = "Proceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014",
    publisher = "IEEE",
    address = "United States",

    }

    Lassen, NB, Madsen, R & Vatrapu, R 2014, Predicting iPhone Sales from iPhone Tweets. in M Reichert, S Rinderle-Ma & G Grossmann (eds), Proceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014. IEEE, Los Alamitos, CA, International Enterprise Distributed Object Computing Conference. Proceedings, vol. 18, pp. 81-90, Ulm, Germany, 01/09/2014. https://doi.org/10.1109/EDOC.2014.20

    Predicting iPhone Sales from iPhone Tweets. / Lassen, Niels Buus; Madsen, Rene; Vatrapu, Ravi.

    Proceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014. ed. / Manfred Reichert; Stefanie Rinderle-Ma; Georg Grossmann. Los Alamitos, CA : IEEE, 2014. p. 81-90 (International Enterprise Distributed Object Computing Conference. Proceedings, Vol. 18).

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    TY - GEN

    T1 - Predicting iPhone Sales from iPhone Tweets

    AU - Lassen, Niels Buus

    AU - Madsen, Rene

    AU - Vatrapu, Ravi

    PY - 2014

    Y1 - 2014

    N2 - Recent research in the field of computational social science have shown how data resulting from the widespread adoption and use of social media channels such as twitter can be used to predict outcomes such as movie revenues, election winners, localized moods, and epidemic outbreaks. Underlying assumptions for this research stream on predictive analytics are that social media actions such as tweeting, liking, commenting and rating are proxies for user/consumer’s attention to a particular object/product and that the shared digital artefact that is persistent can create social influence. In this paper, we demonstrate how social media data from twitter can be used to predict the sales of iPhones. Based on a conceptual model of social data consisting of social graph (actors, actions, activities, and artefacts) and social text (topics, keywords, pronouns, and sentiments), we develop and evaluate a linear regression model that transforms iPhone tweets into a prediction of the quarterly iPhone sales with an average error close to the established prediction models from investment banks. This strong correlation between iPhone tweets and iPhone sales becomes marginally stronger after incorporating sentiments of tweets. We discuss the findings and conclude with implications for predictive analytics with big social data.

    AB - Recent research in the field of computational social science have shown how data resulting from the widespread adoption and use of social media channels such as twitter can be used to predict outcomes such as movie revenues, election winners, localized moods, and epidemic outbreaks. Underlying assumptions for this research stream on predictive analytics are that social media actions such as tweeting, liking, commenting and rating are proxies for user/consumer’s attention to a particular object/product and that the shared digital artefact that is persistent can create social influence. In this paper, we demonstrate how social media data from twitter can be used to predict the sales of iPhones. Based on a conceptual model of social data consisting of social graph (actors, actions, activities, and artefacts) and social text (topics, keywords, pronouns, and sentiments), we develop and evaluate a linear regression model that transforms iPhone tweets into a prediction of the quarterly iPhone sales with an average error close to the established prediction models from investment banks. This strong correlation between iPhone tweets and iPhone sales becomes marginally stronger after incorporating sentiments of tweets. We discuss the findings and conclude with implications for predictive analytics with big social data.

    KW - Data science

    KW - Computational social science

    KW - Social data analytics

    KW - Predictive analytics

    KW - iPhone sales

    KW - iPhone tweets

    KW - Twitter

    U2 - 10.1109/EDOC.2014.20

    DO - 10.1109/EDOC.2014.20

    M3 - Article in proceedings

    SN - 9781479954704

    T3 - International Enterprise Distributed Object Computing Conference. Proceedings

    SP - 81

    EP - 90

    BT - Proceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014

    A2 - Reichert, Manfred

    A2 - Rinderle-Ma, Stefanie

    A2 - Grossmann, Georg

    PB - IEEE

    CY - Los Alamitos, CA

    ER -

    Lassen NB, Madsen R, Vatrapu R. Predicting iPhone Sales from iPhone Tweets. In Reichert M, Rinderle-Ma S, Grossmann G, editors, Proceedings. IEEE 18th International Enterprise Distributed Object Computing Conference, EDOC 2014. Los Alamitos, CA: IEEE. 2014. p. 81-90. (International Enterprise Distributed Object Computing Conference. Proceedings, Vol. 18). https://doi.org/10.1109/EDOC.2014.20