@article{CaspariSadeghi2022, author = {Caspari-Sadeghi, Sima}, title = {Artificial Intelligence in Technology-Enhanced Assessment: A Survey of Machine Learning}, series = {Journal of Educational Technology Systems}, volume = {51}, journal = {Journal of Educational Technology Systems}, number = {3}, publisher = {SAGE Publications}, address = {Sage CA: Los Angeles, CA}, issn = {0047-2395}, doi = {10.1177/00472395221138791}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-11818}, pages = {372 -- 386}, year = {2022}, abstract = {Intelligent assessment, the core of any AI-based educational technology, is defined as embedded, stealth and ubiquitous assessment which uses intelligent techniques to diagnose the current cognitive level, monitor dynamic progress, predict success and update students' profiling continuously. It also uses various technologies, such as learning analytics, educational data mining, intelligent sensors, wearables and machine learning. This can be the key to Precision Education (PE): adaptive, tailored, individualized instruction and learning. This paper explores (a) the applications of Machine Learning (ML) in intelligent assessment, and (b) the use of deep learning models in 'knowledge tracing and student modeling'. The paper concludes by discussing barriers involved in using state-of-the-art ML methods and some suggestions to unleash the power of data and ML to improve educational decision-making.}, language = {en} } @article{QiuMoellerKochetal.2022, author = {Qiu, Ruyi and M{\"o}ller, Malte and Koch, Iring and Mayr, Susanne}, title = {Saliency determines the integration of contextual information into stimulus-response episodes}, series = {Attention, Perception, \& Psychophysics}, volume = {2022}, journal = {Attention, Perception, \& Psychophysics}, number = {84}, publisher = {Springer Nature}, address = {Berlin}, doi = {10.3758/s13414-021-02428-5}, url = {http://nbn-resolving.de/urn:nbn:de:101:1-2023072001343346194537}, pages = {1264 -- 1285}, year = {2022}, abstract = {When humans perform a task, it has been shown that elements of this task, like stimulus (e.g., target and distractor)and response, are bound together into a common episodic representation called stimulus-response episode (or event file).Recently, the context, a completely task-irrelevant stimulus, was found to be integrated into an episode as well. However,instead of being bound directly with the response in a binary fashion, the context modulates the binary binding between thedistractor and response. This finding raises the questions of whether the context can also enter into a binary binding with theresponse, and if so, what determines the way of its integration. In order to resolve these questions, saliency of the contextwas manipulated in three experiments by changing the loudness (Experiment 1) and emotional valence (Experiment 2Aand 2B) of the context. All experiments implemented the four-alternative auditory negative priming paradigm introducedby Mayr and Buchner (2006, Journal of Experimental Psychology: Human Perception and Performance, 32[4], 932-943).Results showed that the integration of context changed as a function of its saliency level. Specifically, the context of lowsaliency was not bound at all, the context of moderate saliency modulated the binary binding between the distractor andresponse, whereas the context of high saliency entered into a binary binding with the response. The current results extend aprevious finding by Hommel (2004, Trends in Cognitive Sciences, 8[11], 494-500) that there is a saliency threshold whichdetermines whether a stimulus is bound or not, by suggesting that a second threshold determines the specific structure (i.e.,binary vs. configural) of the resulting binding.}, language = {en} } @article{Ryzhova2022, author = {Ryzhova, Anna}, title = {Motivated by political beliefs, not only by language: How Russian speakers in Germany compose their transnational news repertoires}, series = {Journalism}, volume = {25}, journal = {Journalism}, number = {1}, publisher = {Sage}, address = {Thousand Oaks}, doi = {10.1177/14648849221130557}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-15485}, pages = {218 -- 237}, year = {2022}, abstract = {Extant research in media and migration has been largely apolitical, focusing on how migrants use media to culturally connect with their homeland and keep their family ties. However, in times of increasing international conflicts and polarisation, such as the years leading up to the Russia's war against Ukraine in 2022, migrant audiences find themselves in a situation when the coverage of national and international politics in the homeland and host country media can differ dramatically. Against this backdrop, this study investigated how Russian speakers living in Germany create and navigate their transnational news repertoires. Grounded in 42 semi-structured interviews with the Russian speakers of the 1 and 1.5 generations in Germany, conducted between May and October 2021, this article identifies three types of transnational news repertoires: (1) politically-motivated news repertoire, (2) truth seeking-motivated news repertoire and (3) situation-motivated news repertoire. The results show that all the news repertoires of all participants are transnational. I argue that in the context of international conflict, not only language but also the participants' political beliefs play an essential role in their news choice. Future research on migrants in political communication should distinguish research not only along with the language of the media outlets but also along with the political ideologies that they project.}, language = {en} } @article{ToepflKravetsRyzhovaetal.2022, author = {T{\"o}pfl, Florian and Kravets, Daria and Ryzhova, Anna and Beseler, Arista}, title = {Who are the plotters behind the pandemic?}, series = {Information, Communication \& Society}, volume = {26 (2023)}, journal = {Information, Communication \& Society}, number = {10}, publisher = {Taylor \& Francis}, address = {London}, doi = {10.1080/1369118X.2022.2065213}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:739-opus4-19119}, pages = {2033 -- 2051}, year = {2022}, abstract = {This article advances extant research that has audited search algorithms for misinformation in four respects. Firstly, this is the first misinformation audit not to implement a national but a cross-national research design. Secondly, it retrieves results not in response to the most popular query terms. Instead, it theorizes two semantic dimensions of search terms and illustrates how they impact the number of misinformative results returned. Furthermore, the analysis not only captures the mere presence of misinformative content but in addition whether the source websites are affiliated with a key misinformation actor (Russia's ruling elites) and whom the conspiracy narratives cast as the malicious plotters. Empirically, the audit compares Covid-19 conspiracy theories in Google search results across 5 key target countries of Russia's foreign communication (Belarus, Estonia, Germany, Ukraine, and the US) and Russia as of November 2020 (N = 5280 search results). It finds that, across all countries, primarily content published by mass media organizations rendered conspiracy theories visible in search results. Conspiratorial content published on websites affiliated with Russia's ruling elites was retrieved in the Belarusian, German and Russian contexts. Across all countries, the majority of conspiracy narratives suspected plotters from China. Malicious actors from the US were insinuated exclusively by sources affiliated with Russia's elites. Overall, conspiracy narratives did not primarily deepen divides within but between national communities, since - across all countries - only plotters from beyond the national borders were blamed. To conclude, the article discusses methodological advice and promising paths of research for future cross-national search engine audits.}, language = {en} }