Original post on eduresearch.social

RE: eduresearch.social/@StellenmarktBildung/116...

Das @dipf_aktuell sucht für das Informationszentrum Bildung eine*n wissenschaftliche*n Mitarbeiter*in zur Promotion für das Verbundprojekt „Desinformation im multilingualen Kontext verstehen und vorbeugen“. Das Teilvorhaben […]

Information Extraction of Doctoral Theses Using Two Different Large Language Models vs Health Services Researchers: Development and #usability Study Background: The “Archive of German language general practice” (ADAM) stores about 500 paper based doctoral theses from 1965 till today. While they have been grouped in different categories no deeper systematic process of information extraction (IE) has been performed yet. Recently developed Large Language Models (LLMs) like ChatGPT have been attributed the potential to help in IE of medical documents. However, there are concerns about hallucination of LLM. Furthermore, there have not been reports regarding their usage in non-recent doctoral theses yet. Objective: To analyze if LLMs can help to extract information from doctor thesis by using GPT-4o and gemini-1.5-flash for paper based doctoral theses in ADAM. Methods: We randomly selected ten doctoral theses from 1965 till 2022. After preprocessing we used two different LLM pipelines, using models of OpenAI and Google, respectively. Pipelines were used to extract dissertation characteristics and generate uniform abstracts. Furthermore, one pooled human-generated abstract was written for comparison. Furthermore, blinded raters were asked to evaluate LLM-generated abstracts in comparison to the human-generated ones. BERTScores were calculated as evaluation metric. Results: Relevant dissertation characteristics and keywords could be extracted for all theses (n=10): name and place of the institute, title of theses, name(s) of author and year of publication. For all except one doctoral thesis an abstract could be generated using GPT-4o, while gemini-1.5-flash provided abstracts in all cases (n=10). The modality of abstract generation showed no influence in raters evaluation using the non-parametric Kruskal-Wallis test for independent groups (P=.44). Creation of LLM-generated abstracts was estimated 24 to 36 times faster than creation by humans. Evaluation metrics showed moderate-to-high semantic similarity (Mean F1 BERT-Score, GPT-4o: 0.72 and Gemini: 0.71). Translation from German into Eng-lish did not result in a loss of information (n=10). Conclusions: An accumulating body of not published doctoral theses makes it difficult to extract relevant evidence. Recent advances in LLMs like ChatGPT, have raised expectations in text mining, but have not yet been used in IE of “historic” medical documents. This #feasibility study sug-gests that both models, GPT-4o and gemini-1.5-flash helped to accurately simplify and con-dense doctoral theses into relevant information while LLM-generated abstracts being per-ceived similar, were semantic similar and taking about thirty times less time in comparison to human-generated ones. This pilot study demonstrates the #feasibility of a regular office scanning workflow and general-purpose LLMs to extract relevant information and produce accurate abstracts from ADAM doctoral theses. Taken together this information could help to better search the scientific background from family medicine from the last 60 years, helping to develop current research questions.

JMIR Formative Res: Information Extraction of Doctoral Theses Using Two Different Large Language Models vs Health Services Researchers: Development and #usability Study #Doktorarbeiten #Informationsextraktion #Sprachmodelle #Gesundheitsforschung #Doktorand

The PhD Wanderer : Essays on Doctoral Studies in Sweden The doctoral period is often described as a linear path, omitting the human dimensions of becoming a scholar. In this volume, the imaginary of the PhD education in Sweden is expanded through the metap...

My edited volume ”The PhD Wanderer” is out in print! The essay anthology of experiences of doctoral studies in Sweden is freely available digitally ( see comment) and now even in its physical form: webshop.publit.com/webshop/5200.... #book #bookrelease #academia #phdstudent #doktorand

⚡ Freie Plätze für #Promovierende: Seit letztem Jahr biete ich in der KSG Edith Stein Berlin ein Co-Working an.

Es gibt noch Platz diesen Freitag (27.06.).
#Promotion #PhD #Promovieren #Arbeiterkind #Wissenschaft #Academia #WissenschaftlicherNachwuchs #PräDoc #Doktorarbeit #Doktorand #Doktorandin

#Zeitmanagement in der #Promotion - wie geht das?
Freya Willicks erklärt es hier im Video - und auch nochmal en detail in ihrem & Holger Angenents #Ratgeber »How to WiMi«.

Zum Buch geht es hier: www.utb.de/doi/book/10....

#Dissertation
#WiMis
#Doktorand
#Doktorandin
#Prokrastination

Doktoratskolleg im Bereich Biomedical und Machine Learning schreibt sechs Doktorand*innenstellen aus - Paris Lodron Universität Salzburg REVELATION, ein Doktoratskolleg im Bereich Biomedical and Machine Learning der Universität Salzburg und der Fachhochschule Salzburg, wird ab März 2025 sechs exzellente Studierende beschäftigen. 4 der ...

Das Doktoratskolleg im Bereich Biomedical und Machine Learning schreibt sechs Doktorand*innenstellen aus👍
Alle Infos findet ihr unter dem Link.
#universitätsalzburg #unisalzburg #salzburg #doktorand
www.plus.ac.at/news/doktora...

Auf #YouTube sprechen Holger Angenent und Freya Willicks, die Autor*innen von »How to WiMi«, mit der Lukas Bischof Hochschulberatung über ihre Toolbox für Promovierende.

Zum #Interview: www.youtube.com/watc...

Zum #Buch: www.utb.de/doi/book/...

#Promotion
#Wissenschaft
#Doktorand
#Doktorandin

Wir suchen: #Doktorand:in oder #PostDoc (m, w, d) zu #Aerosol-#Wolken-Wechselwirkungen > www.tropos.de/institut/beruf-karriere/... / #PhD #PhDPosition #position #Physik #Meteorologie o.ä. / #CAINA...

Wir suchen: #Doktorand/in im Bereich der #Vegetationsfernerkundung zur Bewertung von #Bioaerosol-en (m/w/d): www.tropos.de/institut/beruf-karriere/... / #Master o.ä. in z.B. #Biologie...

Structure And #Radiation) @dfg_public / #Doktorand:in #Meteorologie #Physik #Mathematik #Informatik #ICON #Positions

#Doktorand*in (m/w/div/k.A.) @TROPOS_de gesucht - für einen der vielleicht schönsten Arbeitsplätze in #Leipzig >...

#Doktorand:in oder #PostDoc (m, w, d, k.A.) für die Abt. Experimentelle #Aerosol- und #Wolken-Mikrophysik @TROPOS_de in #Leipzig >...

#Doktorand/in (m,w,div) für Projekt #TRACE gesucht: www.tropos.de/institut/beruf-karriere/... / Transport & Transformation von...

Wir suchen zusammen mit der @UniLeipzig : #Doktorand/in (m, w, div) - Marines organisches #Aerosol und der Einfluss auf Arktische #Wolken. Eine #Promotionsstelle im Rahmen des @dfg_public-TR #AC3TR zum #Klimawandel in #Arktis >...

#Doktorand/in gesucht für Analyse & Interpretation eines Datensatzes der ACE-Expedition www.tropos.de/institut/beruf-karriere/... @ACE_Expedition #sciencejobs

#Doktorand/in für #Hera4HALO gesucht www.tropos.de/institut/beruf-karriere/... #Atmosphärenchemie #HALO ice nucleating #aerosol particles