{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:52:05Z","timestamp":1772934725896,"version":"3.50.1"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2319803"],"award-info":[{"award-number":["2319803"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402505","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"6451-6460","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Adaptive Topic Modeling Framework for Identifying Social Engineering Attacks"],"prefix":"10.1109","author":[{"given":"Manav","family":"Bhasin","sequence":"first","affiliation":[{"name":"San José State University,Computer Science Department,San José,United States of America"}]},{"given":"Faranak","family":"Abri","sequence":"additional","affiliation":[{"name":"San José State University,Computer Science Department,San José,United States of America"}]},{"given":"Jade","family":"Webb","sequence":"additional","affiliation":[{"name":"San José State University,Computer Science Department,San José,United States of America"}]},{"given":"William","family":"Andreopoulos","sequence":"additional","affiliation":[{"name":"San José State University,Computer Science Department,San José,United States of America"}]}],"member":"263","reference":[{"key":"ref1","article-title":"What is social engineering?","volume-title":"Kaspersky","year":"2020"},{"key":"ref2","article-title":"Verizon data breach investigations report: Social engineering insights","volume-title":"Dmarcian","author":"Bowers","year":"2024"},{"key":"ref3","article-title":"Internet crime report","volume-title":"FBI","year":"2022"},{"key":"ref4","article-title":"Spear phishing vs phishing (no-nonsense guide)","volume-title":"Hoxhunt","author":"Sainio","year":"2024"},{"key":"ref5","first-page":"424","article-title":"Semantic analysis of dialogs to detect social engineering attacks","volume-title":"IEEE 9th Int. Conf. Semantic Comput. (ICSC)","author":"Bhakta","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3213711"},{"issue":"11","key":"ref7","first-page":"13609","article-title":"ConvNTM: Conversational neural topic model","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"37","author":"Sun","year":"2023"},{"key":"ref8","article-title":"DailyDialog: A manually labelled multi-turn dialogue dataset","volume-title":"CoRR","volume":"abs\/1710.03957","author":"Li","year":"2017"},{"key":"ref9","article-title":"Towards empathetic open-domain conversation models: A new benchmark and dataset","volume-title":"CoRR","volume":"abs\/1811.00207","author":"Rashkin","year":"2018"},{"issue":"6","key":"ref10","doi-asserted-by":"crossref","DOI":"10.2196\/24435","article-title":"COVID-19 vaccine-related discussion on twitter: Topic modeling and sentiment analysis","volume":"23","author":"Lyu","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"ref11","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489771"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656287"},{"key":"ref14","article-title":"Reuters-21578 Text Categorization Collection","volume-title":"UCI Machine Learning Repository","author":"Lewis","year":"1987"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240363"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08786-3_41"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2516641.2516643"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME46990.2020.00062"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100465"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.tele.2023.101965"},{"key":"ref22","volume-title":"r\/IAmA."},{"key":"ref23","volume-title":"r\/Showerthoughts."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102592"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.findings-emnlp.606","article-title":"DeTiME: Diffusionenhanced topic modeling using encoder-decoder based LLM","volume-title":"Findings Assoc. Comput. Linguistics: EMNLP 2023","author":"Xu","year":"2023"},{"key":"ref26","volume-title":"Auto-encoding variational bayes","author":"Kingma","year":"2022"},{"issue":"24","key":"ref27","doi-asserted-by":"crossref","DOI":"10.3390\/app9245496","article-title":"Topic predictions and optimized recommendation mechanism based on integrated topic modeling and deep neural networks in crowdfunding platforms","volume":"9","author":"Shafqat","year":"2019","journal-title":"Appl. Sci."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","article-title":"Kickstarter","volume-title":"Kickstarter, PBC"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDS52072.2021.00089"},{"issue":"5","key":"ref31","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Networks"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-2007"},{"issue":"1","key":"ref34","first-page":"275","article-title":"Devils, angels, and robots: Tempting destructive users in social media","volume-title":"Proc. Int. AAAI Conf. Web Social Media (ICWSM)","volume":"4","author":"Lee","year":"2010"},{"key":"ref35","article-title":"Weibo","volume-title":"Sina Corporation"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/bf00994018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2016.95"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2187836.2187931"},{"key":"ref40","article-title":"CATBERT: context-aware tiny BERT for detecting social engineering emails","volume-title":"CoRR","author":"Lee","year":"2020"},{"key":"ref41","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"CoRR","volume":"abs\/1810.04805","author":"Devlin","year":"2018"},{"key":"ref42","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","volume-title":"CoRR","volume":"abs\/1910.01108","author":"Sanh","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1958.tb00292.x"},{"issue":"2","key":"ref44","article-title":"Phishing detection using natural language processing and machine learning","volume":"6","author":"Mittal","year":"2022","journal-title":"SMU Data Sci. Rev."},{"key":"ref45","article-title":"BERTopic: Neural topic modeling with a class-based tf-idf procedure","volume-title":"Grootendorst","year":"2022"},{"key":"ref46","article-title":"Sentence-BERT: Sentence embeddings using siamese bert-networks","volume-title":"CoRR","volume":"abs\/1908.10084","author":"Reimers","year":"2019"},{"key":"ref47","volume-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2020"},{"key":"ref48","volume-title":"Dynamic data summarization for hierarchical spatial clustering","author":"Abduaziz","year":"2024"},{"key":"ref49","first-page":"132","volume-title":"A statistical interpretation of term specificity and its application in retrieval. GBR: Taylor Graham Publishing","author":"Jones","year":"1988"},{"key":"ref50","article-title":"Semisupervised sequence tagging with bidirectional language models","volume-title":"CoRR","author":"Peters","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.051"},{"key":"ref52","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref53","article-title":"Claude","volume-title":"Anthropic PBC"},{"key":"ref54","article-title":"Gemini","volume-title":"Google DeepMind"},{"key":"ref55","volume-title":"TopicGPT: A prompt-based topic modeling framework","author":"Pham","year":"2024"},{"key":"ref56","article-title":"GPT-3.5","volume-title":"OpenAI"},{"key":"ref57","volume-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"},{"key":"ref58","volume-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2023"},{"key":"ref59","volume-title":"Solving general arithmetic word problems","author":"Roy","year":"2016"},{"key":"ref60","volume-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"ref61","volume-title":"Program induction by rationale generation: Learning to solve and explain algebraic word problems","author":"Ling","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref63","volume-title":"Chain-of-verification reduces hallucination in large language models","author":"Dhuliawala","year":"2023"},{"key":"ref64","volume-title":"The Art of Deception: Controlling the Human Element of Security","author":"Mitnick","year":"2002"},{"key":"ref65","article-title":"GPT-4o mini","volume-title":"OpenAI"},{"key":"ref66","article-title":"Mistral 7B Instruct v0.3","volume-title":"Mistral AI Team,"},{"key":"ref67","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"CoRR","author":"Hu","year":"2021"},{"key":"ref68","volume-title":"QLoRA: Efficient finetuning of quantized LLMs","author":"Dettmers","year":"2023"},{"key":"ref69","volume-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"ref70","article-title":"GPT-4o","volume-title":"OpenAI"},{"key":"ref71","article-title":"Claude 3.7 Sonnet","volume-title":"Anthropic PBCM"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198245537.001.0001"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488514"},{"key":"ref74","volume-title":"Detecting-SocialEngineering-Attacks","author":"ul Abideen","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3614550"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402505.pdf?arnumber=11402505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:15:41Z","timestamp":1772867741000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402505","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}