Browsing by Author "Malo, Pekka, Assoc. Prof., Aalto University, Department of Information and Service Economy, Finland"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Semantic Content Filtering and Sentiment Analysis for Financial News
    (Aalto University, 2016) Ahlgren, Oskar; Wallenius, Jyrki, Prof., Aalto University, Finland; Korhonen, Pekka, Prof., Aalto University, Finland; Tieto- ja palvelutalouden laitos; Department of Information and Service Economy; Kauppakorkeakoulu; School of Business; Malo, Pekka, Assoc. Prof., Aalto University, Department of Information and Service Economy, Finland
    Today we seldom suffer from lack of information; on the contrary, we often suffer from too much information. As a consequence, important information might go unnoticed, which of course is harmful for individuals, companies, and the economy as a whole. To alleviate the current situation, tools for analyzing financial news are developed in this dissertation. This thesis consists of an introductory part and six research essays. These essays cover three different aspects of these matters. The first two essays cover the data mining and document filtering aspects. In Essay 1, the Wiki-SR method is presented. This approach uses Wikipedia to calculate the relatedness between two concepts, which enhances search queries by implicitly expanding them. This essay also introduces a framework that allows for multiple models in order to improve document modeling. Essay 2 presents a modified Wilks' lambda technique for finding the concepts that best describe a specific document. Even if the proposed approach is light-weight, it is still very efficient. The second group of essays focuses on sentiment analysis. Essay 3 presents an approach that parses sentences and detects any words that might change the polarity of a sentiment-bearing word. This approach shows a significant improvement in accuracy of the analysis. The result was verified with our manually annotated sentiment corpus. A more advanced sentiment corpus was published in Essay 4. This new dual-layer corpus is annotated on both the document and sentence level. As it also allows multiple sentiment-bearing entities in the same sentence, more advanced techniques can be developed. Both corpora are publicly available, and they alleviate the current lack of method evaluation sets in the financial domain. The last two essays put this research in context. Essay 5 studies the research done in the field of sentiment analysis over the last decade. When the keywords given by authors and publishers are compared and the wording of titles and abstracts is analyzed, there are four distinctive areas of interest. Two of them are related to techniques used for sentiment analysis (sentiment classification and sentiment lexicon), and two are common domains of the analysis (reviews and social media). Essay 6 describes the steps needed for a computational approach to financial news analysis as well as commonly used tools and resources.
  • Thumbnail Image
    Item
    Untangling the Application of Text-mining Methods in Information Systems Domain
    (Aalto University, 2019) Upreti, Bikesh Raj; Rossi, Matti, Prof., Aalto University, Department of Information and Service Economy, Finland; Tieto ja palvelujohtamisen laitos; Department of Information and Service Management; Kauppakorkeakoulu; School of Business; Malo, Pekka, Assoc. Prof., Aalto University, Department of Information and Service Economy, Finland
    The advent of digitalization has brought a massive proliferation of unstructured data, producing vast repositories of textual data, from various sources, such as Web sites, academic publications, news articles, blog posts, e-mail, corporate communication platforms, reports, and social media feeds. This proliferation coupled with the upsurge in mobile and Web technologies alongside ever-improving connectivity has led to various digital platforms and applications rapidly achieving mass-market penetration. With the production of textual and other forms of unstructured data certain to continue at unprecedented rates for the foreseeable future, this availability on massive scale presents both opportunities and challenges that researchers and practitioners must address. Ability to utilize text data on a large scale not only provides better coverage in terms of sample size but also opens opportunities to build a deeper understanding of phenomena that otherwise are simply unobservable, "hidden in the noise.'' However, as the world races towards high-volume production, distribution, and consumption of digital text, information systems (IS) researchers are proving slow to start reaping the potential of analyzing textual data. There is an urgent need for methods and techniques that can meet the challenge of analyzing vast bodies of textual data. In an effort to demonstrate potential application of text-mining methods in information systems research, the dissertation presents essays that address large-scale text-based datasets' use in literature analysis and studies of system-specific behavioral outcomes. The first essay deals with identifying the research themes presented in a large body of publications on cloud computing, and the second essay demonstrates the machine-based classification of papers in leading information-systems journals. Of the behavior-focused pieces, the third essay utilizes user-generated content to illustrate system-driven viewing outcomes in the context of binge watching of television shows, and the final essay examines a large volume of content connected with a business-to-business Web portal, reporting on a study of browsing-device-linked differences in interest in marketing material. In addition to the individual essays, the dissertation contributes to the scholarly discussion of text-mining research issues in three important ways. Firstly, it presents a conceptual framework that aids in revealing the fundamentals of text-mining research in terms of two dimensions: research objective and level of text analysis. Secondly, the four essays provide concrete demonstrations of various suitable applications of text-mining. Finally, the dissertation examines the implications of the work, highlighting specific issues and challenges pertaining to text-mining research. The findings and implications of this work should benefit IS researchers and practitioners striving to exploit large volume of textual data.