The purpose of this thesis is to explore the sentiment distributions of Wikipedia concepts. We analyse the sentiment of the entire English Wikipedia corpus, which includes 5,669,867 articles and 1,906,375 talks, by using a lexicon-based method with four different lexicons. Also, we explore the sentiment distributions from a time perspective using the sentiment scores obtained from our selected corpus. The results obtained have been compared not only between articles and talks but also among four lexicons: OL, MPQA, LIWC, and ANEW. Our findings show that among the four lexicons, MPQA has the highest sensitivity and ANEW has the lowest sensitivity to emotional expressions. Wikipedia articles show more sentiments than talks according to OL, MPQA, and LIWC, whereas Wikipedia talks show more sentiments than articles according to ANEW. Besides, the sentiment has a trend regarding time series, and each lexicon has its own bias regarding text describing different things. Moreover, our research provides three interactive widgets for visualising sentiment distributions for Wikipedia concepts regarding the time and geolocation attributes of concepts.

Ontologies play an important role in knowledge representation for sharing information and collaboratively developing knowledge bases. They are changed, adapted and reused in different applications and domains resulting in multiple versions of an ontology. The comparison of different versions and the analysis of changes at a higher level of abstraction may be insightful to understand the changes that were applied to an ontology. While there is existing work on detecting (syntactical) differences and changes in ontologies, there is still a need in analyzing ontology changes at a higher level of abstraction like ontology evolution or refactoring pattern. In our approach we start from a classification of model refactoring patterns found in software engineering for identifying such refactoring patterns in OWL ontologies using DL reasoning to recognize these patterns.

Commonsense reasoning can be seen as a process of identifying dependencies amongst events and actions. Understanding the circumstances surrounding these events requires background knowledge with sufficient breadth to cover a wide variety of domains. In the recent decades, there has been a lot of work in extracting commonsense knowledge, a number of these projects provide their collected data as semantic networks such as ConceptNet and CausalNet. In this thesis, we attempt to undertake the Choice Of Plausible Alternatives (COPA) challenge, a problem set with 1000 questions written in multiple-choice format with a premise and two alternative choices for each question. Our approach differs from previous work by using shortest paths between concepts in a causal graph with the edge weight as causality metric. We use CausalNet as primary network and implement a few design choices to explore the strengths and drawbacks of this approach, and propose an extension using ConceptNet by leveraging its commonsense knowledge base.

Wikipedia is the biggest, free online encyclopaedia that can be expanded by any-one. For the users, who create content on a specific Wikipedia language edition, a social network exists. In this social network users are categorised into different roles. These are normal users, administrators and functional bots. Within the networks, a user can post reviews, suggestions or send simple messages to the "talk page" of another user. Each language in the Wikipedia domain has this type of social network. In this thesis characteristics of the three different roles are analysed in order to learn how they function in one language network of Wikipedia and apply them to another Wikipedia network to identify bots. Timestamps from created posts are analysed to reveal noticeable characteristics referring to continuous messages, message rates and irregular behaviour of a user are discovered. Through this process we show that there exist differences between the roles for the mentioned characteristics.

The availability of digital cameras and the possibility to take photos at no cost lead to an increasing amount of digital photos online and on private computers. The pure amount of data makes approaches that support users in the administration of the photo necessary. As the automatic understanding of photo content is still an unsolved task, metadata is needed for supporting administrative tasks like search or photo work such as the generation of photo books. Meta-information textually describes the depicted scene or consists of information on how good or interesting a photo is. In this thesis, an approach for creating meta-information without additional effort for the user is investigated. Eye tracking data is used to measure the human visual attention. This attention is analyzed with the objective of information creation in the form of metadata. The gaze paths of users working with photos are recorded, for example, while they are searching for photos or while they are just viewing photo collections. Eye tracking hardware is developing fast within the last years. Because of falling prices for sensor hardware such as cameras and more competition on the eye tracker market, the prices are falling, and the usability is increasing. It can be assumed that eye tracking technology can soon be used in everyday devices such as laptops or mobile phones. The exploitation of data, recorded in the background while the user is performing daily tasks with photos, has great potential to generate information without additional effort for the users. The first part of this work deals with the labeling of image region by means of gaze data for describing the depicted scenes in detail. Labeling takes place by assigning object names to specific photo regions. In total, three experiments were conducted for investigating the quality of these assignments in different contexts. In the first experiment, users decided whether a given object can be seen on a photo by pressing a button. In the second study, participants searched for specific photos in an image search application. In the third experiment, gaze data was collected from users playing a game with the task to classify photos regarding given categories. The results of the experiments showed that gaze-based region labeling outperforms baseline approaches in various contexts. In the second part, most important photos in a collection of photos are identified by means of visual attention for the creation of individual photo selections. Users freely viewed photos of a collection without any specific instruction on what to fixate, while their gaze paths were recorded. By comparing gaze-based and baseline photo selections to manually created selections, the worth of eye tracking data in the identification of important photos is shown. In the analysis of the data, the characteristics of gaze data has to be considered, for example, inaccurate and ambiguous data. The aggregation of gaze data, collected from several users, is one suggested approach for dealing with this kind of data. The results of the performed experiments show the value of gaze data as source of information. It allows to benefit from human abilities where algorithms still have problems to perform satisfyingly.