{"id":306,"date":"2024-12-20T18:27:19","date_gmt":"2024-12-20T18:27:19","guid":{"rendered":"https:\/\/blogs.dickinson.edu\/academic-technology\/?p=306"},"modified":"2024-12-20T18:27:19","modified_gmt":"2024-12-20T18:27:19","slug":"how-i-used-ai-in-german-102","status":"publish","type":"post","link":"https:\/\/blogs.dickinson.edu\/academic-technology\/2024\/12\/20\/how-i-used-ai-in-german-102\/","title":{"rendered":"How I used AI in German 102"},"content":{"rendered":"

We used AI several times in German 102, and overall I found it very helpful. The most frequently used tool was the chatbot<\/a> we developed over the summer. You can embed it within a Moodle course along with custom instructions to create scenarios via ChatGPT’s API. Students can also now send a transcript of their conversation to their professor (their chat is not saved within Moodle). We did this for several scenarios to have students role-play a visit to the doctor and to plan a trip to Europe with their partner. I also used it to prepare students for their oral exam. Earlier in the week we created a list of possible questions\/topics that may appear on the exam, I then added those questions to the instructions for the students and instructed the bot to practice with the students and correct any errors it recognizes along with an explanation.<\/p>\n

We also used ChatGPT directly for their final writing assignment. Students wrote their first draft as always, but then submitted their draft to ChatGPT along with this prompt.<\/p>\n

Please correct the text below sentence by sentence. In addition to corrections, provide explanations for each correction suitable for a beginning learning of German along with correct examples of usage<\/p>\n

Students then shared the initial draft, ChatGPT converation history, and the final corrected draft with me. I then gave them a follow-up assignment to be sure they understood the corrections generated by ChatGPT. There were only two errors generated from ChatGPT. Once it marked a sentence as incorrect then gave the exact same sentence as the corrected version. A second time it corrected the final sentence common in German fairly tales. “Und wenn sie nicht gestorben sind dann leben sie noch heute”. It only corrected it for one student. I’m not sure why. It also may seem like a lot of effort for the professor, but it took less time to create a custom assignment (asking them to write a few sentences for each common error) and review it than it had taken earlier in the semester to make and encode each error in their essays.<\/p>\n

Students frequently have trouble with prepositions in German. They need to know their meanings which don’t directly overlap with and English, and for some of the most common prepositions they need to set the case depending on whether it is being used describe a location or if\u00a0 there is movement. To practice these two-way prepositions with location, I had them work in pairs with one student entering a sentence in German using one of these two-way prepositions into Firefly. Based on the image produced, the second student would have to guess the sentence.<\/p>\n

\"Ein<\/a>
Ein Buch liegt auf dem Tisch. (A book is lying on the table)<\/figcaption><\/figure>\n

Finally, I also encouraged students who had trouble with some basic conversation topics\/patterns that in theory they would have learned beforehand to try Univerbal<\/a>. It’s a free (for now) tool that let’s the learner practice based on given topics. As a conversation partner, it does very well. There’s an initial guide\/quiz to estimate the student’s level and then has a tiered conversation. It’s structure and progression tree is similar to DuoLingo, but it’s conversational instead of translation based. It does provide a student progress dashboard, but there’s no useful log or report a student could easily give to their instructor.<\/p>\n

As always if you have questions or if you have examples you’d like to share, email me at bryantt@dickinson.edu<\/strong>.<\/p>\n","protected":false},"excerpt":{"rendered":"

We used AI several times in German 102, and overall I found it very helpful. The most frequently used tool was the chatbot we developed over the summer. You can embed it within a Moodle course along with custom instructions to create scenarios via ChatGPT’s API. Students can also now send a transcript of their […]<\/p>\n","protected":false},"author":776,"featured_media":309,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-306","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/posts\/306","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/users\/776"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/comments?post=306"}],"version-history":[{"count":0,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/posts\/306\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/media\/309"}],"wp:attachment":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/media?parent=306"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/categories?post=306"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/tags?post=306"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}