e-space
Manchester Metropolitan University's Research Repository

    Experiment for Analysing the Impact of Financial Events on Twitter

    Owda, M, Crockett, K, Evans, L, Fernández-Vilas, A and Redondo, R (2017) Experiment for Analysing the Impact of Financial Events on Twitter. In: 17th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP-2017), 21 August 2017 - 23 August 2017, Finland.

    [img]
    Preview

    Download (1MB) | Preview

    Abstract

    Twitter, as the heart of publicly accessible Social Media, is one of the currently used platforms to share financial information and is a valuable source of information for different roles in the financial market. For all these roles, the quality analysis of Twitter as a source of financial information is essential to take decisions. The work in this paper is aligned with the ongoing work of the authors to a solution for irregularity monitoring in the financial market by harnessing data in online social media. To do so, the permeability of a variety of social media data feeders to financial irregularities should be analysed. That is the case of the experiment in this paper by putting the focus on Twitter microblogging platform and checking if this general purpose social media is permeable to a specific financial event. For this, we detail the analysis of Twitter permeability to a specific event in the past few months: the announcement about the merge of Tesco and Booker to create a UK’s Leading Food Business on the 27th January 2017. Both companies Tesco PLC and Booking Group PLC are listed in the main market of LSE (London Stock Exchange). Our findings provide promising evidences to address the problem of real-time detection of irregularities in the financial market via Twitter according to the volume (as a sign of the importance of the irregularity) and to other features (as signs of the potential origin causing the irregularity).

    Impact and Reach

    Statistics

    Activity Overview
    6 month trend
    374Downloads
    6 month trend
    369Hits

    Additional statistics for this dataset are available via IRStats2.

    Altmetric

    Repository staff only

    Edit record Edit record