https://ilcm.informatik.uni-leipzig.de/ Recent content on iLCM - DFG Funded Project Hugo -- gohugo.io en-us Sun, 12 Jun 2022 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2022/06/12/import-functionality-for-wortschatz-corpora-added/ Sun, 12 Jun 2022 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2022/06/12/import-functionality-for-wortschatz-corpora-added/ Corpora from the Wortschatz-Portal can now be easily integrated and used within the LCM. Brief Summary In order to integrate corpora from the Wortschatz-Portal into the tool, the corresponding corpora file must first be downloaded from the portal. This can then be uploaded to the iLCM and automatically transformed into a standard CSV file for import. On the Wortschatz webpage, data is available in a variety of languages, sizes and data-sources. https://ilcm.informatik.uni-leipzig.de/2022/01/07/application-of-the-ilcm-to-detect-gender-differences-in-research-grant-proposals/ Fri, 07 Jan 2022 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2022/01/07/application-of-the-ilcm-to-detect-gender-differences-in-research-grant-proposals/ Brief Summary Research persistently shows that women are underrepresented in most science and engineering fields and obtain fewer research grants than men. In this paper we consider gender-related interests to investigate female and male scientists’ rates of submitted grant proposals and their selection of research topics in research areas of life science, engineering science, physical science and mathematics. Do men and women differ in their research preferences? Do they vary in respect of numbers of submissions and topics? https://ilcm.informatik.uni-leipzig.de/2021/12/17/dynamic-topic-modeling-added-to-ilcm/ Fri, 17 Dec 2021 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2021/12/17/dynamic-topic-modeling-added-to-ilcm/ Dynamic Topic Modeling was added to iLCM as another form of analysis. Brief Summary Classical topic models allow to discover unsupervised topics in document collections and to examine these topics and their distribution within the texts. Dynamic Topic Models (DTM) extended this approach by an additional temporal component. Thus, the changes of topics at different time periods can now be modeled and examined in detail. Especially for large diachronic data sets, this approach represents an exciting extension. https://ilcm.informatik.uni-leipzig.de/2021/10/12/import-of-xlsx-files/ Tue, 12 Oct 2021 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2021/10/12/import-of-xlsx-files/ A new data format is now supported to import data: XLSX Brief Summary Besides the known input formats CSV, REFI and various text files, the latest version of the iLCM can now also import data in XLSX format. This allows to easily save Excel projects and seamlessly explore them further in iLCM using text mining. https://ilcm.informatik.uni-leipzig.de/2020/11/06/gesis-notebooks-jupytercon/ Fri, 06 Nov 2020 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2020/11/06/gesis-notebooks-jupytercon/ Arnim Bleier gave a talk at JupyterCon about GESIS Notebooks: Brief Summary In this talk, we introduce GESIS Notebooks, a public JupyterHub deployment that enables users to persistently import projects using the mechanisms of MyBinder. The talk is relevant for researchers and lecturers that want to work persistently with one of the many existing binder-ready projects as well as for system administrators. Outline Kenan Erdogan and Arnim Bleier offer an overview of GESIS Notebooks notebooks. https://ilcm.informatik.uni-leipzig.de/2020/06/30/reproducibility-made-easy/ Tue, 30 Jun 2020 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2020/06/30/reproducibility-made-easy/ The GESIS notebooks enable scientists to reproduce highly complex research processes with little effort and the greatest possible support. In a web-based interactive working environment, complex computing processes can be performed virtually without having to maintain a powerful and expensive hardware infrastructure. This makes the reproducibility of research much easier; thus the “GESIS notebooks” support compliance with the code of good scientific practice. More Details: https://blog.gesis.org/reproduzierbarkeit-leicht-gemacht-gesis-notebooks-fur-eine-offene-wissenschaft/ https://ilcm.informatik.uni-leipzig.de/2020/04/14/latest-version-enables-refi-import/export/ Tue, 14 Apr 2020 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2020/04/14/latest-version-enables-refi-import/export/ Version 0.996 adds REFI Import and Export The latest release of the iLCM now supports the export of collections, topic model- and classification results in REFI standard. Moreover the export of annotation schema is enabled. In addition the import of codebooks in REFI standard aswell as whole REFI projects is possible. https://ilcm.informatik.uni-leipzig.de/2020/01/23/saving-and-application-of-parameter-presets-now-available/ Thu, 23 Jan 2020 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2020/01/23/saving-and-application-of-parameter-presets-now-available/ Parameter Presets The creation of parameter preconfigurations (presets) is now supported for each implemented analysis via the Task Scheduler. These preconfigurations can then be selected and applied when analyses are performed repeatedly. All available parameters are then set according to their settings in the preset. This simplifies the handling and ensures comparable parameter settings for repeated analyses as well as for the exchange of optimal settings in collaborative projects. This feature is part of the ilcm_standalone release in version 0. https://ilcm.informatik.uni-leipzig.de/2020/01/14/gesis-joins-binder-federation/ Tue, 14 Jan 2020 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2020/01/14/gesis-joins-binder-federation/ GESIS Joins Binder Federation Our Project Partner GESIS joins the Binder Federation. Read more at: https://blog.jupyter.org/gesis-joins-the-binder-federation-8603d878ff77 https://ilcm.informatik.uni-leipzig.de/2019/12/17/announcement-of-refi-standard-support-in-version-1.0/ Tue, 17 Dec 2019 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2019/12/17/announcement-of-refi-standard-support-in-version-1.0/ REFI-QDA Standard support planned for iLCM 1.0 Currently, we are extending the iLCM software to support the REFI-QDA Standard for export and import of projects from varios qualitative data analysis software packages (QDAS). This feature will facilitate mixed method research designs using iLCM’s quantitative text analysis capabilities together with more hermeneutic, interpretive analysis steps of coding text data. Full REFI-QDA support will be built-in in the 1.0 version of ilCM planned for release April 2020. https://ilcm.informatik.uni-leipzig.de/software/download/ Wed, 14 Aug 2019 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/software/download/ Docker Standalone Version The standalone version includes everything to run the application. This includes the app’s R Shiny code together with the required libraries, a Shiny Server, an RStudio Server, a MariaDB database and a solr server. Installation prerequisites In order to run the standalone version of the application the installation of docker is required. Check out https://docs.docker.com/install/ for more details on how to do this. Start the application The application is hosted at dockerhub. https://ilcm.informatik.uni-leipzig.de/2019/08/14/standalone-version-of-ilcm-at-dockerhub-available/ Wed, 14 Aug 2019 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2019/08/14/standalone-version-of-ilcm-at-dockerhub-available/ Standalone Version There is now a version available at dockerhub that uses a single container. This already includes a running database, a solr-instance, a spacy-environment, the R libraries and the iLCM Shiny-App all. All services will be running right from the start. The image can easily be started as shown in software. https://ilcm.informatik.uni-leipzig.de/software/add_features/ Tue, 05 Mar 2019 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/software/add_features/ The iLCM allows you to include other functionalities to the existing environment. Here we will show you the steps necessary. The integration of a keyness-analysis will be utilized as a running example. Several Steps need to be considered. 1. UI The architecture of the Shiny App is split in 2 parts. The UI part, where the userinterface is definded, and the server part, where the logic behind the ui is given. https://ilcm.informatik.uni-leipzig.de/software/install_instructions/ Wed, 07 Nov 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/software/install_instructions/ Prerequisite You need a running installation of docker, docker-compose. Make sure you can call docker commands without sudo. When you are working in a windows home edition environment you are forced to use the docker toolbox instead. The use of the iLCM based on docker-Toolbox is working but not recommend due to limitations caused by third-party-software (virtualbox). Download Install File Please download the right file for your operating system from http://ilcm. https://ilcm.informatik.uni-leipzig.de/2018/09/12/ilcm-at-summer-academy-of-the-studienstiftung-des-deutschen-volkes-german-academic-scholarship-foundation/ Wed, 12 Sep 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2018/09/12/ilcm-at-summer-academy-of-the-studienstiftung-des-deutschen-volkes-german-academic-scholarship-foundation/ Computational Social Sciences - Methods of Computer-Aided Social Science Research Using Current Issues as Examples In the age of Big Data, the interdisciplinary cooperation of various scientific disciplines and Computer Science is a central prerequisite for the implementation of many innovative research ideas, but also for many professions. A new discipline, computational social science, is emerging for the social sciences that is dedicated to the description, analysis and explanation of social phenomena in the broadest sense on the basis of large amounts of data, novel data types and with the help of state-of-the-art data-processing technologies. https://ilcm.informatik.uni-leipzig.de/ilcm/css/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/ilcm/css/ The manual evaluation of qualitative data is an integral part in the set of methods of empirical social science research in various disciplines. Since the availability of increasingly large amounts of digital or retro-digitized text, there has also been a growing interest in the evaluation of large amounts of text using computer-assisted methods. iLCM is based on a previous software prototype developed in the research project ePol. Furthermore, the iLCM infrastructure integrates a fully functional script environment. https://ilcm.informatik.uni-leipzig.de/contact/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/contact/ Dr. Arnim Bleier Computational Social Science Data Science Unter Sachsenhausen 6-8 50667 Köln Germany +49 (0221) 47694 - 514 E-Mail: arnim•bleier[at]gesis•org Prof. Dr. Gerhard Heyer Abteilung Automatische Sprachverarbeitung Institut für Informatik Universität Leipzig Augustusplatz 10 04109 Leipzig Germany +49 (0341) 97 - 32231 E-Mail: heyer@informatik.uni-leipzig.de https://ilcm.informatik.uni-leipzig.de/software/documentation/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/software/documentation/ On this page we will provide a detailed documentation including installation and usage. A starting guide can be downloaded here: Download Starting Guide An updated documentation together with tutorials is currently in preparation. https://ilcm.informatik.uni-leipzig.de/2018/05/02/ilcm-on-lrec-2018/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/2018/05/02/ilcm-on-lrec-2018/ The LREC 2018 conference has accepted our paper co-authored by the iLCM team: Andreas Niekler, Arnim Bleier, Christian Kahmann, Lisa Posch, Gregor Wiedemann, Kenan Erdogan, Gerhard Heyer, Markus Strohmaier iLCM - A Virtual Research Infrastructure for Large-Scale Qualitative Data The paper was accepted as a poster demonstration. The poster can be found here: See you in Japan! Abstract: The iLCM project pursues the development of an integrated research environment for the analysis of structured and unstructured data in a ‘Software as a Service’ architecture (SaaS). https://ilcm.informatik.uni-leipzig.de/impress/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/impress/ Anbieterkennzeichnung Hinweise zur Haftung 1. Anbieterkennzeichnung Diensteanbieter dieses Internetangebots im Sinne von §6 TDG bzw. §10 Abs. 1, 2 MDStV sowie verantwortlich im Sinne von §10 Abs. 3 MDStV: Prof. Dr. Gerhard Heyer Institut für Informatik Universität Leipzig Augustusplatz 10 D-04109 Leipzig Tel.: +49 – 341 – 97 32231 Fax: +49 – 341 – 97 32299 E-Mail: heyer@informatik.uni-leipzig.de URL: http://www.asv.informatik.uni-leipzig.de 2. Hinweise zur Haftung Anbieter sind für die eigenen Inhalte, die sie zur Nutzung bereithalten, nach den allgemeinen Gesetzen verantwortlich. https://ilcm.informatik.uni-leipzig.de/ilcm/integration/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/ilcm/integration/ The LCM is optimized for the generic processing of large amounts of text data. However, for experienced researchers, it is easy to identify needs for analyzes that go beyond the generic usage of text mining. The combination of standardized computer-linguistic evaluations in the LCM and customized evaluations in the ORC environment is an elegant solution. Therefore, the ORC environment is integrated into the iLCM architecture. Interfaces and functions will be implemented in the iLCM to easily exchange data objects between the LCM and the ORC environment. https://ilcm.informatik.uni-leipzig.de/ilcm/lcm/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/ilcm/lcm/ The iLCM is not a stand-alone software, but rather an infrastructure consisting of a multitude of components including a document database (MariaDB), an NLP pipeline for processing different text mining processes (In R statistical language), a full-text index (Solr) and a web application (R Shiny). To make the infrastructure available as a decentralized installation for other projects it is embedded in a virtual machine ensemble (Docker), which can be easily set up with predefined configuration scripts. https://ilcm.informatik.uni-leipzig.de/ilcm/orc/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/ilcm/orc/ The GUI-based framework of the LCM enables end-users to conduct standardized text mining workflows without any programming skills. However, individual and innovative research designs often demand more flexibility which is hard to achieve with generic pre-defined workflows accessed by point-and-click GUIs. https://ilcm.informatik.uni-leipzig.de/project_team/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/project_team/ Andreas Niekler: is a postdoctoral research assistant at the Institute of Computer Science at the University of Leipzig in the Department of Natural Language Processing. He develops computer-based content analysis methods for the social sciences with a focus on machine learning and data management. In a former project he developed the content analysis platform Leipzig Corpus Minder (LCM). He is also a lecturer in text mining and data management and is involved in projects for the discussion and assessment of media quality and data journalism. https://ilcm.informatik.uni-leipzig.de/ilcm/ilcm/ Wed, 02 May 2018 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/ilcm/ilcm/ The iLCM project pursues the development of an integrated research environment for the analysis of structured and unstructured data in a ‘Software as a Service’ architecture (SaaS). The research environment addresses requirements for the quantitative evaluation of large amounts of qualitative data using text mining methods and requirements for the reproducibility of data-driven research designs in the social sciences. The iLCM research environment is based on the Leipzig Corpus Miner (LCM), a decentralized SaaS application for the analysis of very large amounts of news texts developed in a previous Digital Humanities project. https://ilcm.informatik.uni-leipzig.de/ilcm/ Mon, 01 Jan 0001 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/ilcm/ What is iLCM? The iLCM project pursues the development of an integrated research environment for the analysis of structured and unstructured data in a “Software as a Service” architecture (SaaS). The research environment addresses requirements for the quantitative evaluation of large amounts of qualitative data using text mining methods and requirements for the reproducibility of data-driven research designs in the social sciences. The iLCM research environment is based on the Leipzig Corpus Miner (LCM), a decentralized SaaS application for the analysis of very large amounts of news texts developed in a previous Digital Humanities project. https://ilcm.informatik.uni-leipzig.de/1/01/01/ Mon, 01 Jan 0001 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/1/01/01/ https://ilcm.informatik.uni-leipzig.de/software/github/ Mon, 01 Jan 0001 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/software/github/ https://ilcm.informatik.uni-leipzig.de/software/lcm_legacy/ Mon, 01 Jan 0001 00:00:00 +0000 https://ilcm.informatik.uni-leipzig.de/software/lcm_legacy/