sayzarddeshmukh (@deshmukhpatelai)
사용자에게 http://tokkah.com을 공유하며, Tokkah이 실제 영화 클립을 세로 피드 형식으로 제공하는 틱톡 스타일의 영화 발견 서비스임을 소개합니다. 끝없는 검색 없이 빠르게 좋은 영화를 찾게 해주는 점을 차별화 요소로 강조합니다.
ITmedia NEWS (@itmedia_news)
18일에 발생한 YouTube 장애의 원인은 추천 시스템(추천 알고리즘)이었다는 보도성 트윗입니다. 플랫폼 수준의 추천 모델/시스템 문제로 서비스 이상이 발생했다는 점에서 실서비스에 적용된 AI 시스템의 안정성 이슈를 시사합니다.
JTI@phpmacher #RSS nutzen: Sicher. Immer noch populär. Ob als Eingangsformat für andere Medien oder direkte Nutzung durch Menschen.
Gibt diverse Systeme die lokal aggregieren und filtern, auch self-hostable. Teilweise über die eingebetteten #Metadaten, teilweise mit #Regex gegen andere Inhaltsfelder.
Der Schritt von da zu einer Art #Bayesfilter oder den NN wie sie #rspamd zur Klassifizierung nutzt oder sogar einem SLM/kleineren #LLM auf #Ollama, ggf. mit #TPU / #APU Support sollte überschaubar groß sein.
Eins der Probleme wird aber die zunehmend schlechte Feedqualität was Tags/Metadaten und der notorische (wenn gleich sehr verständliche) Hang zur Nicht-Auslieferung des Volltext im Feed sein. Da müsste man ggf auf Verdacht das Original fetchen, ggf. als zweite Stufe.
Und natürlich ist ein #Recommender-System was deutlich anderes als ein mehr oder minder ausgefeilter #Classifier. Aber lassen wir das...
PCI RRWhat does a PCI RR #recommender of #RegisteredReports do?
1) Authors submit article & suggest several recommenders in their area & with whom they have no conflicts of interest. Once the authors click "Submit", invitations are automatically sent to suggested recommenders
2) Invited recommenders receive an email invitation to handle the submission. They can accept, decline, or ignore. Many people are invited at once, so invitees don't need to feel pressured to accept every invitation
1/n
CCIA Europe3️⃣ Pay particular attention to #AgeAssurance requirements
4️⃣ Promote neutral design of online services
5️⃣ Acknowledge the value of #recommender systems
👇 Check our full submission to learn more: https://ccianet.org/library/ccia-europes-feedback-guidelines-on-protection-of-minors-online-under-the-dsa/
MottGScholar Inbox: Personalized Paper Recommendations for Scientists
Scholar Inbox is a new open-access platform designed to address the challenges researchers face in staying current with the rapidly expanding volume of scientific literature. We provide personalized recommendations, continuous updates from open-access archives (arXiv, bioRxiv, etc.), visual paper summaries, semantic search,...
Scholar Inbox: Personalized Paper Recommendations for Scientists
Scholar Inbox is a new open-access platform designed to address the challenges researchers face in staying current with the rapidly expanding volume of scientific literature. We provide personalized recommendations, continuous updates from open-access archives (arXiv, bioRxiv, etc.), visual paper summaries, semantic search, and a range of tools to streamline research workflows and promote open research access. The platform's personalized recommendation system is trained on user ratings, ensuring that recommendations are tailored to individual researchers' interests. To further enhance the user experience, Scholar Inbox also offers a map of science that provides an overview of research across domains, enabling users to easily explore specific topics. We use this map to address the cold start problem common in recommender systems, as well as an active learning strategy that iteratively prompts users to rate a selection of papers, allowing the system to learn user preferences quickly. We evaluate the quality of our recommendation system on a novel dataset of 800k user ratings, which we make publicly available, as well as via an extensive user study. https://www.scholar-inbox.com/
SIRUP: Search-based Interactive Recommendations with User Profiles
App allowing you to experiment with different methods of getting AI to recommend a book for you, eg. you can pick a vibe that describes what kind of emotional space you are in with respect to book picking, etc.
https://sirup.mpi-inf.mpg.de/dataset-goodreads
The research paper describing this work:
https://dl.acm.org/doi/10.1145/3616855.3635692
B!SON#TIBopenness | Du schreibst an einem Paper und fragst Dich, in welchem Journal es gut aufgehoben ist? Am liebsten #OpenAccess, aber ohne, dass Du Dich um nervige Publikationskosten (#APC) kümmern musst?
Unser Tipp: Teste doch mal #B!SON, unseren freien #OAJournal #Recommender!
Einfach hier loslegen: http://service.tib.eu/bison oder B!SON in 90 Sekunden erklären lassen: https://doi.org/10.5446/62603
(1/2)
Claus Atzenbeck 🇪🇺Excited to announce that our article “Narrative co-creation with SPORE: a spatial #hypertext based #narrative #recommender system” has been published in the NRHM journal as #OpenAccess! 🎉 Co-authored with Daniel Roßner and Sam Brooker. Check it out here: https://doi.org/10.1080/13614568.2024.2402704
#elit #eliterature #recsys
#elit #eliterature #recsys
There was also a paper related to Spatial #Hypertext-oriented #Recommender Systems presented by Daniel Roßner at this week's ACM Hypertext @ht in Poznań, co-authored by Lisa Eidloth and myself: “PAIRWISE – From Spatial Structure to Knowledge”. It is available as #OpenAccess at https://doi.org/10.1145/3648188.3675137
