@article{KrestelChikkamathHeweletal.2021, author = {Krestel, Ralf and Chikkamath, Renukswamy and Hewel, Christoph and Risch, Julian}, title = {A survey on deep learning for patent analysis}, series = {World patent information}, volume = {65}, journal = {World patent information}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0172-2190}, doi = {10.1016/j.wpi.2021.102035}, pages = {13}, year = {2021}, abstract = {Patent document collections are an immense source of knowledge for research and innovation communities worldwide. The rapid growth of the number of patent documents poses an enormous challenge for retrieving and analyzing information from this source in an effective manner. Based on deep learning methods for natural language processing, novel approaches have been developed in the field of patent analysis. The goal of these approaches is to reduce costs by automating tasks that previously only domain experts could solve. In this article, we provide a comprehensive survey of the application of deep learning for patent analysis. We summarize the state-of-the-art techniques and describe how they are applied to various tasks in the patent domain. In a detailed discussion, we categorize 40 papers based on the dataset, the representation, and the deep learning architecture that were used, as well as the patent analysis task that was targeted. With our survey, we aim to foster future research at the intersection of patent analysis and deep learning and we conclude by listing promising paths for future work.}, language = {en} } @phdthesis{Gruetze2018, author = {Gr{\"u}tze, Toni}, title = {Adding value to text with user-generated content}, school = {Universit{\"a}t Potsdam}, pages = {ii, 114}, year = {2018}, abstract = {In recent years, the ever-growing amount of documents on the Web as well as in closed systems for private or business contexts led to a considerable increase of valuable textual information about topics, events, and entities. It is a truism that the majority of information (i.e., business-relevant data) is only available in unstructured textual form. The text mining research field comprises various practice areas that have the common goal of harvesting high-quality information from textual data. These information help addressing users' information needs. In this thesis, we utilize the knowledge represented in user-generated content (UGC) originating from various social media services to improve text mining results. These social media platforms provide a plethora of information with varying focuses. In many cases, an essential feature of such platforms is to share relevant content with a peer group. Thus, the data exchanged in these communities tend to be focused on the interests of the user base. The popularity of social media services is growing continuously and the inherent knowledge is available to be utilized. We show that this knowledge can be used for three different tasks. Initially, we demonstrate that when searching persons with ambiguous names, the information from Wikipedia can be bootstrapped to group web search results according to the individuals occurring in the documents. We introduce two models and different means to handle persons missing in the UGC source. We show that the proposed approaches outperform traditional algorithms for search result clustering. Secondly, we discuss how the categorization of texts according to continuously changing community-generated folksonomies helps users to identify new information related to their interests. We specifically target temporal changes in the UGC and show how they influence the quality of different tag recommendation approaches. Finally, we introduce an algorithm to attempt the entity linking problem, a necessity for harvesting entity knowledge from large text collections. The goal is the linkage of mentions within the documents with their real-world entities. A major focus lies on the efficient derivation of coherent links. For each of the contributions, we provide a wide range of experiments on various text corpora as well as different sources of UGC. The evaluation shows the added value that the usage of these sources provides and confirms the appropriateness of leveraging user-generated content to serve different information needs.}, language = {en} } @article{AbramovaBatzelModesti2022, author = {Abramova, Olga and Batzel, Katharina and Modesti, Daniela}, title = {Collective response to the health crisis among German Twitter users}, series = {International Journal of Information Management Data Insights}, volume = {2}, journal = {International Journal of Information Management Data Insights}, number = {2}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2667-0968}, doi = {10.1016/j.jjimei.2022.100126}, pages = {13}, year = {2022}, abstract = {We used structural topic modeling to analyze over 800,000 German tweets about COVID-19 to answer the questions: What patterns emerge in tweets as a response to a health crisis? And how do topics discussed change over time? The study leans on the goals associated with the health information seeking (GAINS) model, discerning whether a post aims at tackling and eliminating the problem (i.e., problem-focused) or managing the emotions (i.e., emotion-focused); whether it strives to maximize positive outcomes (promotion focus) or to minimize negative outcomes (prevention focus). The findings indicate four clusters salient in public reactions: 1) "Understanding" (problem-promotion); 2) "Action planning" (problem-prevention); 3) "Hope" (emotion-promotion) and 4) "Reassurance" (emotion-prevention). Public communication is volatile over time, and a shift is evidenced from self-centered to community-centered topics within 4.5 weeks. Our study illustrates social media text mining's potential to quickly and efficiently extract public opinions and reactions. Monitoring fears and trending topics enable policymakers to rapidly respond to deviant behavior, like resistive attitudes toward containment measures or deteriorating physical health. Healthcare workers can use the insights to provide mental health services for battling anxiety or extensive loneliness from staying home.}, language = {en} }