{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T08:11:40Z","timestamp":1778227900815,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819203659","type":"print"},{"value":"9789819203666","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-92-0366-6_35","type":"book-chapter","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T07:23:44Z","timestamp":1778225024000},"page":"578-594","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Driven Online Aggregation for\u00a0Unstructured Text Analytics"],"prefix":"10.1007","author":[{"given":"Chao","family":"Hui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weizheng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjie","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfeng","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueguo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,9]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Mozafari, B., Panda, A., Milner, H., Madden, S., Stoica, I.: BlinkDB: queries with bounded errors and bounded response times on very large data. In: EuroSys 13, pp. 29\u201342 (2013)","DOI":"10.1145\/2465351.2465355"},{"issue":"8","key":"35_CR2","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.3390\/electronics9081295","volume":"9","author":"M Ahmed","year":"2020","unstructured":"Ahmed, M., Seraj, R., Islam, S.M.S.: The k-means algorithm: a comprehensive survey and performance evaluation. Electronics 9(8), 1295 (2020)","journal-title":"Electronics"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Armbrust, M., et al.: Structured streaming: a declarative API for real-time applications in Apache spark. In: SIGMOD 18, pp. 601\u2013613 (2018)","DOI":"10.1145\/3183713.3190664"},{"key":"35_CR4","unstructured":"BerriAI: LiteLLM (2024). https:\/\/github.com\/BerriAI\/litellm. Accessed 16 June 2025"},{"key":"35_CR5","unstructured":"Bose, B.: BBC News classification (2019). https:\/\/kaggle.com\/competitions\/learn-ai-bbc. Kaggle"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: a survey. ACM Comput. Surv. 54(2) (2021)","DOI":"10.1145\/3440756"},{"key":"35_CR7","unstructured":"Cherguelain, A.: Company documents dataset. Kaggle (2024). https:\/\/www.kaggle.com\/datasets\/ayoubcherguelaine\/company-documents-dataset"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Dai, H., et al: UQE: a query engine for unstructured databases. In: NeurIPS 2024, vol.\u00a037, pp. 29807\u201329838 (2024)","DOI":"10.52202\/079017-0938"},{"issue":"2","key":"35_CR9","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1145\/304181.304208","volume":"28","author":"PJ Haas","year":"1999","unstructured":"Haas, P.J., Hellerstein, J.M.: Ripple joins for online aggregation. SIGMOD Rec. 28(2), 287\u2013298 (1999)","journal-title":"SIGMOD Rec."},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"He, R., McAuley, J.: Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering. In: WWW 2016, pp. 507\u2013517 (2016)","DOI":"10.1145\/2872427.2883037"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Hellerstein, J.M., Haas, P.J., Wang, H.J.: Online aggregation. In: SIGMOD 1997, pp. 171\u2013182 (1997)","DOI":"10.1145\/253260.253291"},{"issue":"3","key":"35_CR12","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Joshi, S., Jermaine, C.: Robust stratified sampling plans for low selectivity queries. In: ICDE 2008, pp. 199\u2013208. IEEE (2008)","DOI":"10.1109\/ICDE.2008.4497428"},{"key":"35_CR14","unstructured":"Kreps, J., Narkhede, N., Rao, J., et\u00a0al.: Kafka: a distributed messaging system for log processing. In: NetDB 2011, pp.\u00a01\u20137 (2011)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with pagedattention. In: SOSP 2023, pp. 611\u2013626 (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Wen, Y., Yuan, X.: Online aggregation: a review. In: Web Information Systems and Applications, pp. 103\u2013114 (2018)","DOI":"10.1007\/978-3-030-02934-0_10"},{"key":"35_CR17","unstructured":"Liu, S., et al.: Optimizing LLM queries in relational workloads. In: MLSys 2025 (2025)"},{"key":"35_CR18","doi-asserted-by":"publisher","unstructured":"Neyman, J.: On the two different aspects of the representative method: the method of stratified sampling and the method of purposive selection. In: Kotz, S., Johnson, N.L. (eds) Breakthroughs in Statistics. Springer Series in Statistics, pp. 123\u2013150. Springer, New York (1992). https:\/\/doi.org\/10.1007\/978-1-4612-4380-9_12","DOI":"10.1007\/978-1-4612-4380-9_12"},{"issue":"1","key":"35_CR19","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/BF00140664","volume":"5","author":"F Olken","year":"1995","unstructured":"Olken, F., Rotem, D.: Random sampling from databases: a survey. Stat. Comput. 5(1), 25\u201342 (1995)","journal-title":"Stat. Comput."},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Pang, B., Lee, L.: Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales. arXiv preprint cs\/0506075 (2005)","DOI":"10.3115\/1219840.1219855"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Park, Y., Mozafari, B., Sorenson, J., Wang, J.: VerdictDB: universalizing approximate query processing. In: SIGMOD 2018, pp. 1461\u20131476 (2018)","DOI":"10.1145\/3183713.3196905"},{"issue":"11","key":"35_CR22","first-page":"4171","volume":"18","author":"L Patel","year":"2025","unstructured":"Patel, L., et al.: Semantic operators and their optimization: towards AI-based data analytics with accuracy guarantees. PVLDB 18(11), 4171\u20134184 (2025)","journal-title":"PVLDB"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: EMNLP 2019 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Su, Y., Zhang, J., Lu, J.: The resume corpus: a large dataset for research in information extraction systems. In: CIS 2019, pp. 375\u2013378 (2019)","DOI":"10.1109\/CIS.2019.00087"},{"key":"35_CR25","unstructured":"arXiv.org submitters: arXiv dataset (2024). https:\/\/www.kaggle.com\/dsv\/7548853"},{"issue":"7","key":"35_CR26","doi-asserted-by":"publisher","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","volume":"55","author":"M Wankhade","year":"2022","unstructured":"Wankhade, M., Rao, A.C.S., Kulkarni, C.: A survey on sentiment analysis methods, applications, and challenges. Artif. Intell. Rev. 55(7), 5731\u20135780 (2022)","journal-title":"Artif. Intell. Rev."}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-0366-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T07:23:54Z","timestamp":1778225034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-0366-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819203659","9789819203666"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-0366-6_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2026.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}