{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:50:59Z","timestamp":1774716659072,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:00:00Z","timestamp":1751846400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:00:00Z","timestamp":1751846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Recent advancements in Artificial Intelligence (AI), notably the development of Large Language Models (LLMs) and text-to-image diffusion models, have facilitated the creation of realistic textual content and images. Specifically, platforms like ChatGPT and Midjourney have simplified the creation of high-quality text and visuals with minimal expertise and cost. The increasing sophistication of Generative AI presents challenges in ensuring the integrity of news, media, and information quality, making it increasingly difficult to distinguish between real and artificially generated textual and visual content. Our work addressed this problem in two ways. First, by means of ChatGPT and Midjourney, we created a comprehensive novel multimodal news corpus named\n                    <jats:italic>SyN24News<\/jats:italic>\n                    based on the\n                    <jats:italic>N24News<\/jats:italic>\n                    corpus, on which we evaluated our model. Second, we developed a novel explainable synthetic news detector for discriminating between real and synthetic news articles. We leveraged a Neural Additive Model (NAM)-like network structure that ensures effect separation by handling input data in separate subnetworks. Complex structures and patterns are extracted by deep features from unstructured data, i.e., images and texts, using fine-tuned VGG and DistilBERT subnetworks. We ensured further explainability by individually processing carefully chosen handcrafted text and image features in simple Multilayer Perceptrons (MLPs), allowing for graphical interpretation of corresponding structured effects. Our findings indicate that textual information are the main drivers in the decision-making finding process. Structured textual effects, particularly Flesch-Kincaid reading ease and sentiment, have a much higher influence on the classification outcome than visual features such as dissimilarity and homogeneity.\n                  <\/jats:p>","DOI":"10.1007\/s10462-025-11188-9","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T01:49:48Z","timestamp":1751852988000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Decoding synthetic news: an interpretable multimodal framework for the classification of news articles in a novel news corpus"],"prefix":"10.1007","volume":"58","author":[{"given":"Michael","family":"Schlee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gillian","family":"Kant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Ehrling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"S\u00e4fken","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Kneib","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,7]]},"reference":[{"key":"11188_CR1","unstructured":"Agarwal R, Frosst N, Zhang X, Caruana R, Hinton GE (2020) Neural additive models: Interpretable machine learning with neural nets. CoRR, abs\/2004.13912,, arXiv:2004.13912"},{"key":"11188_CR2","doi-asserted-by":"crossref","unstructured":"Amoroso R, Morelli D, Cornia M, Baraldi L, Del Bimbo A, Cucchiara R (2023) Parents and children: Distinguishing multimodal deepfakes from natural images. arXiv preprint arXiv:2304.00500","DOI":"10.1145\/3665497"},{"issue":"1","key":"11188_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1136\/bmjsem-2023-001568","volume":"9","author":"N Anderson","year":"2023","unstructured":"Anderson N, Belavy DL, Perle SM, Hendricks S, Hespanhol L, Verhagen E, Memon AR (2023) Ai did not write this manuscript, or did it? can we trick the ai text detector into generated texts? the potential future of chatgpt and ai in sports & exercise medicine manuscript generation. BMJ Open Sport Exercise Med 9(1):1","journal-title":"BMJ Open Sport Exercise Med"},{"issue":"2","key":"11188_CR4","doi-asserted-by":"publisher","first-page":"190","DOI":"10.7861\/fhj.2022-0013","volume":"9","author":"A Arora","year":"2022","unstructured":"Arora A, Arora A (2022) Generative adversarial networks and synthetic patient data: current challenges and future perspectives. Future Healthcare J 9(2):190\u2013193","journal-title":"Future Healthcare J"},{"key":"11188_CR5","doi-asserted-by":"crossref","unstructured":"Balabaeva K, Kovalchuk S (2022) Neural additive models for explainable heart attack prediction. In: Groen D, de Mulatier C, Paszynski M, Krzhizhanovskaya VV, Dongarra JJ, Sloot PMA (Eds.), Computational science - iccs 2022, pp. 113-121","DOI":"10.1007\/978-3-031-08757-8_11"},{"key":"11188_CR6","doi-asserted-by":"crossref","unstructured":"Bird JJ, Lotfi A (2023) Cifake: Image classification and explainable identification of ai-generated synthetic images","DOI":"10.1109\/ACCESS.2024.3356122"},{"key":"11188_CR7","unstructured":"Dawber A, Tomlinson H (2023) Donald trump deepfakes: Ai\u2019s role on twitter. Retrieved from https:\/\/www.thetimes.com\/businessmoney\/technology\/article\/donald-trump-deepfakes-ai-twitter-g50n7vnbm (Accessed on the 12th of August, 2024)"},{"issue":"2","key":"11188_CR8","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1080\/14703297.2023.2190148","volume":"61","author":"RE Debby","year":"2024","unstructured":"Debby RE, Cotton PAC, Shipway JR (2024) Chatting and cheating: ensuring academic integrity in the era of chatgpt. Innov Educ Teach Int 61(2):228\u2013239. https:\/\/doi.org\/10.1080\/14703297.2023.2190148","journal-title":"Innov Educ Teach Int"},{"issue":"1","key":"11188_CR9","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1038\/s41746-023-00819-6","volume":"6","author":"CA Gao","year":"2023","unstructured":"Gao CA, Howard FM, Markov NS, Dyer EC, Ramesh S, Luo Y, Pearson AT (2023) Comparing scientific abstracts generated by chatgpt to real abstracts with detectors and blinded human reviewers. npj Digital Med 6(1):75. https:\/\/doi.org\/10.1038\/s41746-023-00819-6","journal-title":"npj Digital Med"},{"issue":"1","key":"11188_CR10","doi-asserted-by":"publisher","first-page":"84","DOI":"10.22329\/il.v38i1.5068","volume":"38","author":"A Gelfert","year":"2018","unstructured":"Gelfert A (2018) Fake news: a definition. Inf Logic 38(1):84\u2013117. https:\/\/doi.org\/10.22329\/il.v38i1.5068","journal-title":"Inf Logic"},{"key":"11188_CR11","unstructured":"Guo X, Chen Y (2024) Generative ai for synthetic data generation: Methods, challenges and the future. Retrieved from arXiv:2403.04190"},{"issue":"6","key":"11188_CR12","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","volume":"3","author":"RM Haralick","year":"1973","unstructured":"Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybernet 3(6):610\u2013621","journal-title":"IEEE Trans Syst Man Cybernet"},{"key":"11188_CR13","doi-asserted-by":"crossref","unstructured":"Hastie T, Tibshirani R (2017) Generalized additive models","DOI":"10.1201\/9780203753781"},{"key":"11188_CR14","unstructured":"Huan K (2023) Ai-generated photos of pope francis: A new reality. Retrieved from https:\/\/www.nytimes.com\/2023\/04\/08\/technology\/ai-photospope-francis.html (Accessed on the 12th of August, 2024)"},{"issue":"1","key":"11188_CR15","doi-asserted-by":"publisher","first-page":"12187","DOI":"10.1038\/s41598-023-38964-3","volume":"13","author":"H Ibrahim","year":"2023","unstructured":"Ibrahim H, Liu F, Asim R, Battu B, Benabderrahmane S, Alhafni B, Zaki Y (2023) Perception, performance, and detectability of conversational artificial intelligence across 32 university courses. Sci Rep 13(1):12187. https:\/\/doi.org\/10.1038\/s41598-023-38964-3","journal-title":"Sci Rep"},{"key":"11188_CR16","doi-asserted-by":"crossref","unstructured":"Joshi G, Walambe R, Kotecha K (2021) A review on explainability in multimodal deep neural nets. CoRR, abs\/2105.07878, 1, arXiv:2105.07878","DOI":"10.1109\/ACCESS.2021.3070212"},{"key":"11188_CR17","doi-asserted-by":"crossref","unstructured":"Kincaid JP, Fishburne Jr RP, Rogers RL, Chissom BS (1975) Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel","DOI":"10.21236\/ADA006655"},{"key":"11188_CR18","unstructured":"Krizhevsky A, Hinton G (2009) Cifake: Real and ai-generated synthetic images. Retrieved from https:\/\/www.kaggle.com\/datasets\/birdy654\/cifake-real-and-aigenerated-synthetic-images (Accessed on the 12th of August, 2024)"},{"key":"11188_CR19","unstructured":"Li Y, Liu X, Wang X, Wang S, Lin W (2024) Fakebench: Uncover the achilles\u2019 heels of fake images with large multimodal models. arXiv preprint arXiv:2404.13306"},{"key":"11188_CR20","unstructured":"Loria S, et al (2018) Textblob: Simplified text processing - documentation. Retrieved from https:\/\/textblob.readthedocs.io\/en\/dev\/ (Accessed on the 12th of August, 2024)"},{"key":"11188_CR21","doi-asserted-by":"crossref","unstructured":"Lyu Y, Liang PP, Deng Z, Salakhutdinov R, Morency L-P (2022) Dime: Fine-grained interpretations of multimodal models via disentangled local explanations. Proceedings of the 2022 aaai\/acm conference on ai, ethics, and society, p. 455-467","DOI":"10.1145\/3514094.3534148"},{"issue":"2","key":"11188_CR22","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1038\/s41576-022-00532-2","volume":"24","author":"G Novakovsky","year":"2023","unstructured":"Novakovsky G, Dexter N, Libbrecht MW, Wasserman WW, Mostafavi S (2023) Obtaining genetics insights from deep learning via explainable artificial intelligence. Nature Rev Genet 24(2):125\u2013137","journal-title":"Nature Rev Genet"},{"key":"11188_CR23","first-page":"1","volume":"10","author":"J Oppenlaender","year":"2023","unstructured":"Oppenlaender J (2023) A taxonomy of prompt modifiers for text-to-image generation. Behav Inform Technol 10:1\u201314","journal-title":"Behav Inform Technol"},{"key":"11188_CR24","doi-asserted-by":"crossref","unstructured":"Park DH, Hendricks LA, Akata Z, Rohrbach A, Schiele B, Darrell T, Rohrbach M (2018) Multimodal explanations: Justifying decisions and pointing to the evidence. Accessed from arXiv:1802.08129)","DOI":"10.1109\/CVPR.2018.00915"},{"key":"11188_CR25","unstructured":"Robertson K (2023) The new york times passes 10 million subscribers. Retrieved from https:\/\/www.nytimes.com\/2023\/11\/08\/business\/media\/newyork-times-q3-earnings.html (Accessed on the 12 Aug, 2024)"},{"issue":"2","key":"11188_CR26","doi-asserted-by":"publisher","first-page":"15","DOI":"10.17645\/mac.v11i2.6315","volume":"11","author":"R Rodr\u00edguez-Ferr\u00e1ndiz","year":"2023","unstructured":"Rodr\u00edguez-Ferr\u00e1ndiz R (2023) An overview of the fake news phenomenon: from untruth-driven to post-truth-driven approaches. Media Commun 11(2):15\u201329","journal-title":"Media Commun"},{"key":"11188_CR27","unstructured":"Roose K (2022) Ai and artists: The evolving relationship. (Accessed on the 12th of Aug 2024)"},{"key":"11188_CR28","unstructured":"R\u00fcgamer D, Kolb C, Klein N (2022) Semi-structured distributional regression: Extending structured additive models by arbitrary deep neural networks and data modalities. arXiv:2002.05777"},{"key":"11188_CR29","unstructured":"R\u00fcgamer D, Kolb C, Weber T, Kook L, Nagler T (2024) Generalizing orthogonalization for models with non-linearities"},{"key":"11188_CR30","doi-asserted-by":"crossref","unstructured":"Salau AO, Jain S (2019) Feature extraction: A survey of the types, techniques, applications. 2019 international conference on signal processing and communication (icsc)","DOI":"10.1109\/ICSC45622.2019.8938371"},{"key":"11188_CR31","doi-asserted-by":"publisher","first-page":"50851","DOI":"10.1109\/ACCESS.2023.3276480","volume":"11","author":"D Salvi","year":"2023","unstructured":"Salvi D, Hosler B, Bestagini P, Stamm MC, Tubaro S (2023) Timit-tts: A text-to-speech dataset for multimodal synthetic media detection. IEEE Access 11:50851\u201350866","journal-title":"IEEE Access"},{"issue":"2","key":"11188_CR32","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1093\/pnasnexus\/pgae035","volume":"3","author":"A Simchon","year":"2024","unstructured":"Simchon A, Edwards M, Lewandowsky S (2024) The persuasive effects of political microtargeting in the age of generative artificial intelligence. PNAS Nexus 3(2):35","journal-title":"PNAS Nexus"},{"key":"11188_CR33","doi-asserted-by":"crossref","unstructured":"Tsai Y-HH, Ma M, Yang M, Salakhutdinov R, Morency L-P (2020, November) Multimodal routing: Improving local and global interpretability of multimodal language analysis. Proceedings of the 2020 conference on empirical methods in natural language processing (emnlp), pp. 1823-1833","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"11188_CR34","doi-asserted-by":"crossref","unstructured":"Utkin LV, Satyukov ED, Konstantinov AV (2022, mar) Survnam: The machine learning survival model explanation. Neural Netw., 147(C):81-102, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0893608021004949","DOI":"10.1016\/j.neunet.2021.12.015"},{"key":"11188_CR35","doi-asserted-by":"crossref","unstructured":"Vetter J, Lim K, Dijkstra TMH, Dargaville PA, Kohlbacher O, Macke JH, Poets CF (2023) Neonatal apnea and hypopnea prediction in infants with robin sequence with neural additive models for time series. medRxiv, 1, https:\/\/www.medrxiv.org\/content\/10.1101\/2023.03.14.23287021v1.full.pdf","DOI":"10.1101\/2023.03.14.23287021"},{"key":"11188_CR36","unstructured":"Wang Z, Shan X, Zhang X, Yang J (2022, June). N24News: A new dataset for multimodal news classification. In: Calzolari N et al (Eds.), Proceedings of the thirteenth language resources and evaluation conference, pp. 6768-6775"},{"key":"11188_CR37","doi-asserted-by":"crossref","unstructured":"Xu D, Fan S, Kankanhalli M (2023) Combating misinformation in the era of generative ai models. Proceedings of the 31st acm international conference on multimedia (p. 9291-9298)","DOI":"10.1145\/3581783.3612704"},{"key":"11188_CR38","doi-asserted-by":"crossref","unstructured":"Yu P, Chen J, Feng X, Xia Z (2024) Cheat: A large-scale dataset for detecting chatgpt-written abstracts. arXiv:2304.12008","DOI":"10.1109\/TBDATA.2025.3536929"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11188-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-025-11188-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11188-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T18:09:15Z","timestamp":1757700555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-025-11188-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,7]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["11188"],"URL":"https:\/\/doi.org\/10.1007\/s10462-025-11188-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4921351\/v1","asserted-by":"object"}]},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,7]]},"assertion":[{"value":"6 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"302"}}