Challenges in Heterogeneous Web Data Analytics - Case Finnish Growth Companies in Social Media
Tutkimustuotos › › vertaisarvioitu
|Otsikko||17th International Academic MindTrek Conference, October 1-4, 2013, Tampere, Finland|
|DOI - pysyväislinkit|
|Tila||Julkaistu - 2013|
|OKM-julkaisutyyppi||A4 Artikkeli konferenssijulkaisussa|
Diverse data about various phenomena are implicitly available in the modern web. In particular websites categorized as social media provide rich and heterogeneous data about various entities such as people, corporations, brands as well as their properties and relationships. An analyst who seeks to leverage this diverse data is faced with the challenge of integrating and making sense of a set of heterogeneous data sources. In this paper, we provide an introduction and a problem statement for heterogeneous web data analytics. To further highlight and discuss practical challenges, we introduce a case study of Finnish growth companies in social media. Instead of a purely data-driven approach, the presented approach is rooted in the idea that an analyst can actively participate in the data collection and integration process, while the process can still retain repeatability and transparency. The key contribution of this paper is the statement of the challenges related to heterogeneous web data analytics.