Genre and domain influence an author\'s style of writing and therefore a text\'s characteristics. Natural language processing is prone to such variations in textual characteristics: it is said to be genre and domain dependent. This thesis investigates genre and domain dependencies in sentiment analysis. Its goal is to support the development of robust sentiment analysis approaches that work well and in a predictable manner under different conditions, i.e. for different genres and domains. Initially, we show that a prototypical approach to sentiment analysis -- viz. a supervised machine learning model based on word n-gram features -- performs differently on gold standards that originate from differing genres and domains, but performs similarly on gold standards that originate from resembling genres and domains. We show that these gold standards differ in certain textual characteristics, viz. their domain complexity. We find a strong linear relation between our approach\'s accuracy on a particular gold standard and its domain complexity, which we then use to estimate our approach\'s accuracy. Subsequently, we use certain textual characteristics -- viz. domain complexity, domain similarity, and readability -- in a variety of applications. Domain complexity and domain similarity measures are used to determine parameter settings in two tasks. Domain complexity guides us in model selection for in-domain polarity classification, viz. in decisions regarding word n-gram model order and word n-gram feature selection. Domain complexity and domain similarity guide us in domain adaptation. We propose a novel domain adaptation scheme and apply it to cross-domain polarity classification in semi- and unsupervised domain adaptation scenarios. Readability is used for feature engineering. We propose to adopt readability gradings, readability indicators as well as word and syntax distributions as features for subjectivity classification. Moreover, we generalize a framework for modeling and representing negation in machine learning-based sentiment analysis. This framework is applied to in-domain and cross-domain polarity classification. We investigate the relation between implicit and explicit negation modeling, the influence of negation scope detection methods, and the efficiency of the framework in different domains. Finally, we carry out a case study in which we transfer the core methods of our thesis -- viz. domain complexity-based accuracy estimation, domain complexity-based model selection, and negation modeling -- to a gold standard that originates from a genre and domain hitherto not used in this thesis.

Genre and domain influence an author\''s style of writing and therefore a text\''s characteristics. Natural language processing is prone to such variations in textual characteristics: it is said to be genre and domain dependent. This thesis investigates genre and domain dependencies in sentiment analysis. Its goal is to support the development of robust sentiment analysis approaches that work well and in a predictable manner under different conditions, i.e. for different genres and domains. Initially, we show that a prototypical approach to sentiment analysis -- viz. a supervised machine learning model based on word n-gram features -- performs differently on gold standards that originate from differing genres and domains, but performs similarly on gold standards that originate from resembling genres and domains. We show that these gold standards differ in certain textual characteristics, viz. their domain complexity. We find a strong linear relation between our approach\''s accuracy on a particular gold standard and its domain complexity, which we then use to estimate our approach\''s accuracy. Subsequently, we use certain textual characteristics -- viz. domain complexity, domain similarity, and readability -- in a variety of applications. Domain complexity and domain similarity measures are used to determine parameter settings in two tasks. Domain complexity guides us in model selection for in-domain polarity classification, viz. in decisions regarding word n-gram model order and word n-gram feature selection. Domain complexity and domain similarity guide us in domain adaptation. We propose a novel domain adaptation scheme and apply it to cross-domain polarity classification in semi- and unsupervised domain adaptation scenarios. Readability is used for feature engineering. We propose to adopt readability gradings, readability indicators as well as word and syntax distributions as features for subjectivity classification. Moreover, we generalize a framework for modeling and representing negation in machine learning-based sentiment analysis. This framework is applied to in-domain and cross-domain polarity classification. We investigate the relation between implicit and explicit negation modeling, the influence of negation scope detection methods, and the efficiency of the framework in different domains. Finally, we carry out a case study in which we transfer the core methods of our thesis -- viz. domain complexity-based accuracy estimation, domain complexity-based model selection, and negation modeling -- to a gold standard that originates from a genre and domain hitherto not used in this thesis.

Erweiterte Fassung (2019) des gleichnamigen Beitrages aus Wahrnehmung – Erkenntnis – Vermittlung. Hildesheim, Zürich, New York: Olms Verlag, 2013 (Fs. Auhagen), 248-259

In dieser Dissertation werden vier Studien durchgeführt, um die acht Arten von Räumen in Mensch-Natur-Systemen für die Widerstandsfähigkeit von Städten vorzuschlagen, die Verbesserung von städtischen Grünflächen unter qualitativen und quantitativen Gesichtspunkten zu analysieren, die Beziehung zwischen UGSLandschaftsmerkmalen und menschlichen Emotionen zu bestimmen und das Konzept der selbstlernenden Stadt für die städtische Raumplanung zu veranschaulichen. (1). Unterschiedliche Strategien in den Acht-Typen-Räumen in Mensch-Natur-Systemen. (2). Verbesserung der städtischen Grünflächen mit natürlichem Angebot und menschlicher Nachfrage. (3). Das Konzept der selbstlernenden Stadt für urbane Nachhaltigkeit. (4) Für die städtische Nachhaltigkeit erfordert die Planung eine Neubewertung der Verbindungen zwischen den verschiedenen menschlichen und natürlichen Systemen mit den Wechselwirkungen zwischen Bedarf und Versorgung Städtische Räume sind komplex, weisen aber in verschiedenen Methoden und Konzepten Regelmäßigkeiten auf. Für eine nachhaltige Entwicklung in Städten sind kreative Denkansätze für die Umsetzung und Integration von sich überschneidenden Räumen, Elementen und Kulturen in städtischen Mensch-Natur-Systemen erforderlich. Um eine nachhaltige Stadt zu schaffen, sind urbane Räume unerlässlich. / This dissertation conducts four studies to propose the eight-type spaces in human-natural systems for city resilience, to analyze the improvement of urban green spaces from quality and quantity perspectives, to determine the relationship between UGS landscape characteristics and human emotions and to illustrate the concept of city self-learning for urban space planning. (1). Different strategies in the eight-type spaces across human-natural systems. (2). Improving urban green spaces with natural supply and human demand. (3). The concept of city self-learning for urban sustainability. (4) For urban sustainability, planning requires reevaluating the connections between different human-natural systems with the interactions of demands and supplies. Dissertation title: Exploring Urban Spaces across Human-Natural systems And the Potential to Enhance City Resilience Urban spaces are complex but have regularity in several methods and concepts. For sustainable development in cities, creative ways to think about implementations and integrations utilize crossing spaces, elements, and cultures in urban human-natural systems. To make a sustainable city, urban spaces are essential.