Abstract—Many relations existing in DBpedia are missing in Wikipedia yielding up an information gap between the semantic web and the social web. Inserting these missing relations requires to automatically discover Wikipedia conventions. From pairs linked by a property p in DBpedia, we find path queries that link the same pairs in Wikipedia. We make the hypothesis that the shortest path query with maximal containment captures the Wikipedia convention for p. We computed missing links and conventions for different DBpedia queries. Next, we inserted some missing links according to computed conventions in Wikipedia and evaluated Wikipedians feedback. Nearly all contributions has been accepted. In this paper, we detail the path indexing algorithms, the results of evaluations and give some details about social feedback. Keywords-Wikipedia Conventions; DBpedia; Wikipedia I.

In this paper an approach based on Wikipedia link structure for sense disambiguation is presented and evaluated. Wikipedia is used as a reference to obtain lexicographic relationships and in combination with statistical information extraction it is possible to deduce concepts related to the terms extracted from a corpus. In addition, since the corpus covers a representation of a part of the real world the corpus itself is used as training data for choosing the sense which best fit the corpus. 1

ABSTRACT Web search is seeing a paradigm shift from keyword based search to an entity-centric organization of web data. To support web search with this deeper level of understanding, a web-scale entity linking system must have 3 key properties: First, its feature extraction must be robust to the diversity of web documents and their varied writing styles and content structures. Second, it must maintain high-precision linking for "tail" (unpopular) entities that is robust to the existence of confounding entities outside of the knowledge base and entity profiles with minimal information. Finally, the system must represent large-scale knowledge bases with a scalable and powerful feature representation. We have built and deployed a web-scale unsupervised entity linking system for a commercial search engine that addresses these requirements by combining new developments in sparse signal recovery to identify the most discriminative features from noisy, free-text web documents; explicit modeling of out-of-knowledge-base entities to improve precision at the tail; and the development of a new phrase-unigram language model to efficiently capture high-order dependencies in lexical features. Using a knowledge base of 100M unique people from a popular social networking site, we present experimental results in the challenging domain of people-linking at the tail, where most entities have limited web presence. Our experimental results show that this system substantially improves on the precision-recall tradeoff over baseline methods, achieving precision over 95% with recall over 60%.

Collaborative content creation inevitably reaches situations where different points of view lead to conflict. We focus on Wikipedia, the free encyclopedia anyone may edit, where disputes about content in controversial articles often reflect larger societal debates. While Wikipedia has a public edit history and discussion section for every article, the substance of these sections is difficult to phantom for Wikipedia users interested in the development of an article and in locating which topics were most controversial. In this paper we present Contropedia, a tool that augments Wikipedia articles and gives insight into the development of controversial topics. Contropedia uses an efficient language agnostic measure based on the edit history that focuses on wiki links to easily identify which topics within a Wikipedia article have been most controversial and when.

An overview of web mining in societal benefit areas

Standard-Nutzungsbedingungen: Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden. Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen. Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. http://ftp.zew.de/pub/zew-docs/dp/dp12053.pdf Die Dis cus si on Pape rs die nen einer mög lichst schnel len Ver brei tung von neue ren For schungs arbei ten des ZEW. Die Bei trä ge lie gen in allei ni ger Ver ant wor tung der Auto ren und stel len nicht not wen di ger wei se die Mei nung des ZEW dar. Terms of use: Documents in EconStor may Dis cus si on Papers are inten ded to make results of ZEW research prompt ly avai la ble to other eco no mists in order to encou ra ge dis cus si on and sug gesti ons for revi si ons. The aut hors are sole ly respon si ble for the con tents which do not neces sa ri ly repre sent the opi ni on of the ZEW. Non-Technical Summary The free online encyclopedia Wikipedia represents a prototypical case of peer production of an information good on a large online platform. This production mode is nowadays widely spread on the Internet. Peer production is governed neither by the market nor by a firm. A mass of producers usually contributes small fragments of the overall output without remuneration. In the absence of market signals and hierarchical decisions, it is important for platform administrators to understand how producers decide where to contribute. On a complex and dynamic platform like Wikipedia, this decision is expected to depend on the way the content is organized. One main organizing principle for content on wikis are hyperlinks, i.e. links that allow to browse from one article to another. We study how the position of an article in the hyperlink network is related to how much content is provided by users, and which role the network position of an article plays in attracting the contributions of new authors. The network we consider is defined by incoming hyperlinks on articles within German Wikipedia. We chose a sample of more than 7, 000 articles belonging to a particular category ("Oekonomie" -"Economics") observed over a period of 153 weeks. For this sample, we compute centrality measures within the category and on the entire German Wikipedia. Thus we can compare links from articles that are semantically close to links coming from articles that are on average less closely related. We find that increases in the number of links from the category are strongly associated with increases in page length. In particular, greater centrality of an article is associated with new authors contributing to the article. Evidence for a relation between links from outside the category to page length turns out to be rather weak. Social network analysis reveals that the category "Economics" is, like many networks, constituted by one large cluster and other single articles or small network components that are disconnected from it. Getting connected to the large cluster raises the page length and its rate of change sizeably in the following weeks. The size of contributions associated with new links is in the order of magnitude of several words to one or two sentences. While this may seem not very large, many weekly changes on Wikipedia articles are of this size. Das Wichtigste in Kürze Abstract When contributing content to large and highly structured online platforms like Wikipedia, producers of user-generated content have to decide where to contribute. This decision is expected to depend on the way the content is organized. We analyse whether the hyperlinks on Wikipedia channel the attention of producers towards more central articles. We observe a sample 7, 635 articles belonging to the category economics on the German Wikipedia over 153 weeks and we measure their centrality both within this category and in the network of over one million German Wikipedia articles. Our analysis reveals that an additional link from the observed category is associated with around 140 bytes of additional content and with an increase in the number of authors by 0.5. The relation of links from outside the category to content creation is much weaker. JEL-Classification: L14, D83

Abstract not found

Reference sites play an increasingly important role in learning processes. Teachers use these sites in order to identify topics that should be covered by a course or a lecture. Learners visit online encyclopedias and dictionaries to find alternative explanations of concepts, to learn more about a topic, or to better understand the context of a concept. Ideally, a course or lecture should cover all key concepts of the topic that it encompasses, but often time constraints prevent complete coverage. In this paper, we propose an approach to identify missing references and key concepts in a corpus of educational lectures. For this purpose, we link concepts in educational material to the organizational and linking structure of Wikipedia. Identifying missing resources enables learners to improve their understanding of a topic, and allows teachers to investigate whether their learning material covers all necessary concepts.

Reference sites play an increasingly important role in learning processes. Teachers use these sites in order to identify topics that should be covered by a course or a lecture. Learners visit online encyclopedias and dictionaries to find alternative explanations of concepts, to learn more about a topic, or to better understand the context of a concept. Ideally, a course or lecture should cover all key concepts of the topic that it covers, but often time constraints prevent complete coverage. In this paper, we propose an approach to identify missing references and key concepts in a corpus of educational lectures. For this purpose, we link concepts in educational material to the organizational and linking structure of Wikipedia. Identifying missing resources enables learners to improve their understanding of a topic, and allows teachers to investigate whether their learning material covers all necessary concepts.

Abstract—Hand-made hyperlinks are increasingly outnumbered by automatically generated links, which are usually based on text similarity or some sort of recommendation algorithm. In this paper we explore the current linking and appreciation of automatically generated links. To what extent do they prevail on the Web, in what forms do they appear, and do users think that generated link are just as good as human-created links? To answer these questions we first propose a model for extracting contextual information of a hyperlink. Second, we developed a hyperlink ranker to assigned relevance to each existing human generated link. With the outcomes of the hyperlink ranker, together with another two recommendation strategies, we performed a user study with over 100 participants. Results indicate that automated links are ‘good enough’, and even preferred in some user contexts. Still, they do not provide the deeper knowledge as expressed by human authors. I.