{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:16Z","timestamp":1740122836466,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T00:00:00Z","timestamp":1651795200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T00:00:00Z","timestamp":1651795200000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s11042-022-13042-4","type":"journal-article","created":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T06:03:36Z","timestamp":1651817016000},"page":"9047-9064","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Unsupervised tweets categorization using semantic and statistical features"],"prefix":"10.1007","volume":"82","author":[{"given":"Maibam Debina","family":"Devi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8908-9395","authenticated-orcid":false,"given":"Navanath","family":"Saharia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,6]]},"reference":[{"issue":"4","key":"13042_CR1","first-page":"30","volume":"131","author":"V Agarwal","year":"2015","unstructured":"Agarwal V (2015) Research on data preprocessing and categorization technique for smartphone review analysis. Int J Comput Appl 131(4):30\u201336","journal-title":"Int J Comput Appl"},{"key":"13042_CR2","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1016\/j.ins.2021.08.042","volume":"577","author":"A Ali","year":"2021","unstructured":"Ali A, Zhu Y, Zakarya M (2021) Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks. Inf Sci 577:852\u2013870","journal-title":"Inf Sci"},{"key":"13042_CR3","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1016\/j.neucom.2016.08.045","volume":"216","author":"MB Aouicha","year":"2016","unstructured":"Aouicha MB, Taieb MAH, Hamadou AB (2016) Lwcr: multi-layered Wikipedia representation for computing word relatedness. Neurocomputing 216:816\u2013843","journal-title":"Neurocomputing"},{"key":"13042_CR4","doi-asserted-by":"crossref","unstructured":"Arachie C, Gaur M, Anzaroot S, Groves W, Zhang K, Jaimes A (2020) Unsupervised detection of sub-events in large scale disasters. In: AAAI Conference on Artificial Intelligence, vol 34, pp 354\u2013361","DOI":"10.1609\/aaai.v34i01.5370"},{"key":"13042_CR5","doi-asserted-by":"crossref","unstructured":"Bafna P, Pramod D, Vaidya A (2016) Document clustering: Tf-idf approach. In: International Conference on Electrical, Electronics, and Optimization Techniques. IEEE, pp 61\u201366","DOI":"10.1109\/ICEEOT.2016.7754750"},{"key":"13042_CR6","unstructured":"Bradley PS, Fayyad U, Reina C, et al (1998) Scaling em (expectation-maximization) clustering to large databases. Technical Report MSR-TR-98-35, Microsoft Research"},{"issue":"15","key":"13042_CR7","doi-asserted-by":"publisher","first-page":"10809","DOI":"10.1007\/s00521-018-3442-0","volume":"32","author":"J Chen","year":"2020","unstructured":"Chen J, Yan S, Wong K-C (2020) Verbal aggression detection on Twitter comments: Convolutional neural network for short-text sentiment analysis. Neural Comput Appl 32(15):10809\u201310818","journal-title":"Neural Comput Appl"},{"key":"13042_CR8","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.sbspro.2011.10.577","volume":"27","author":"E Clark","year":"2011","unstructured":"Clark E, Araki K (2011) Text normalization in social media: progress, problems and applications for a pre-processing system of casual english. Procedia-Soc Behav Sci 27:2\u201311","journal-title":"Procedia-Soc Behav Sci"},{"key":"13042_CR9","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.inffus.2016.01.002","volume":"31","author":"JM Cotelo","year":"2016","unstructured":"Cotelo JM, Cruz FL, Enr\u00edquez F, Troyano JA (2016) Tweet categorization by combining content and structural knowledge. Inf Fusion 31:54\u201364","journal-title":"Inf Fusion"},{"key":"13042_CR10","doi-asserted-by":"publisher","first-page":"101801","DOI":"10.1016\/j.is.2021.101801","volume":"101","author":"KE Daouadi","year":"2021","unstructured":"Daouadi KE, Reba\u00ef RZ, Amous I (2021) Optimizing semantic deep forest for tweet topic classification. Inf Syst 101:101801","journal-title":"Inf Syst"},{"issue":"1","key":"13042_CR11","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/BF01890115","volume":"1","author":"WHE Day","year":"1984","unstructured":"Day WHE, Edelsbrunner H (1984) Efficient algorithms for agglomerative hierarchical clustering methods. J Class 1(1):7\u201324","journal-title":"J Class"},{"key":"13042_CR12","doi-asserted-by":"crossref","unstructured":"Devi MD, Saharia N (2020) Exploiting topic modelling to classify sentiment from lyrics. In: International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, pp 411\u2013423","DOI":"10.1007\/978-981-15-6318-8_34"},{"key":"13042_CR13","unstructured":"Dos Santos C, Gatti M (2014) Deep convolutional neural networks for sentiment analysis of short texts. In: International Conference on Computational Linguistics, pp 69\u201378"},{"key":"13042_CR14","unstructured":"Ester M, Kriegel H-P, Sander J, Xu X, et al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the International Conference on Knowledge Discovery and Data Mining. AAAI Press, Portland, pp 226\u2013231"},{"key":"13042_CR15","doi-asserted-by":"crossref","unstructured":"Firdaus DH, Suyanto S (2020) Topic-based tweet clustering for public figures using ant clustering. In: 3rd International Seminar on Research of Information Technology and Intelligent Systems, pp 476\u2013481","DOI":"10.1109\/ISRITI51436.2020.9315449"},{"key":"13042_CR16","unstructured":"Go A, Bhayani R, Huang L (2009) Twitter sentiment classification using distant supervision. CS224N project report, Stanford 1(12)"},{"issue":"1","key":"13042_CR17","first-page":"100","volume":"28","author":"JA Hartigan","year":"1979","unstructured":"Hartigan JA, Wong MA (1979) Algorithm as 136: A k-means clustering algorithm. J R Stat Soc 28(1):100\u2013108","journal-title":"J R Stat Soc"},{"key":"13042_CR18","doi-asserted-by":"publisher","first-page":"23253","DOI":"10.1109\/ACCESS.2017.2776930","volume":"6","author":"Z Jianqiang","year":"2018","unstructured":"Jianqiang Z, Xiaolin G, Xuejun Z (2018) Deep convolution neural networks for Twitter sentiment analysis. IEEE Access 6:23253\u201323260","journal-title":"IEEE Access"},{"key":"13042_CR19","doi-asserted-by":"crossref","unstructured":"Jianqiang Z, Xueliang C (2015) Combining semantic and prior polarity for boosting Twitter sentiment analysis. In: International Conference on Smart City. IEEE, pp 832\u2013837","DOI":"10.1109\/SmartCity.2015.171"},{"key":"13042_CR20","unstructured":"Link A-K (2018) Challenges for dbscan: Closely adjacent clusters and varying densities"},{"key":"13042_CR21","doi-asserted-by":"crossref","unstructured":"Meetei LS, Singh TD, Borgohain SK, Bandyopadhyay S (2021) Low resource language specific pre-processing and features for sentiment analysis task. Lang Resour Eval:1\u201323","DOI":"10.1007\/s10579-021-09541-9"},{"issue":"4","key":"13042_CR22","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/S0019-9958(58)90229-8","volume":"1","author":"GA Miller","year":"1958","unstructured":"Miller GA, Newman EB, Friedman EA (1958) Length-frequency statistics for written english. Inf Control 1(4):370\u2013389","journal-title":"Inf Control"},{"key":"13042_CR23","doi-asserted-by":"crossref","unstructured":"Miyamoto S, Suzuki S, Takumi S (2012) Clustering in tweets using a fuzzy neighborhood model. In: International Conference on Fuzzy Systems, Brisbane, pp 1\u20136","DOI":"10.1109\/FUZZ-IEEE.2012.6250800"},{"issue":"6","key":"13042_CR24","first-page":"1336","volume":"39","author":"MM Mojiri","year":"2020","unstructured":"Mojiri MM, Ravanmehr R (2020) Event detection in Twitter using multi timing chained windows. Comput Inf 39(6):1336\u20131359","journal-title":"Comput Inf"},{"key":"13042_CR25","doi-asserted-by":"crossref","unstructured":"Munkov\u00e1 D, Munk M, Voz\u00e1r M (2013) Influence of stop-words removal on sequence patterns identification within comparable corpora. In: International Conference on ICT Innovations. Springer, pp 67\u201376","DOI":"10.1007\/978-3-319-01466-1_6"},{"key":"13042_CR26","unstructured":"Norvig P (2013) English letter frequency counts: Mayzner revisited or etaoin srhldcu. https:\/\/norvig.com\/mayzner.html"},{"key":"13042_CR27","doi-asserted-by":"crossref","unstructured":"O\u2019Connor B, Krieger M, Ahn D (2010) Tweetmotif: exploratory search and topic summarization for Twitter. In: Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, George Washington University, pp 384\u2013385","DOI":"10.1609\/icwsm.v4i1.14008"},{"key":"13042_CR28","doi-asserted-by":"crossref","unstructured":"Park S, Kim Y (2016) Building thesaurus lexicon using dictionary-based approach for sentiment classification. In: International Conference on Software Engineering Research, Management and Applications. IEEE, pp 39\u201344","DOI":"10.1109\/SERA.2016.7516126"},{"key":"13042_CR29","unstructured":"Rosa KD, Shah R, Lin B, Gershman A, Frederking R (2011) Topical clustering of tweets. Proceedings of the ACM SIGIR workshop on Social Web Search and Mining, Analysis under crisis, vol 63"},{"key":"13042_CR30","unstructured":"Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv:1609.04747"},{"key":"13042_CR31","doi-asserted-by":"crossref","unstructured":"Rudrapal D, Das A (2017) Measuring the limit of semantic divergence for english tweets. In: Recent Advances in Natural Language Processing, Varna, pp 618\u2013624","DOI":"10.26615\/978-954-452-049-6_080"},{"key":"13042_CR32","doi-asserted-by":"crossref","unstructured":"Saharia N (2015) Detecting emotion from short messages on Nepal earthquake. In: International Conference on Speech Technology and Human-Computer Dialogue. IEEE, Bucharest, pp 1\u20135","DOI":"10.1109\/SPED.2015.7343089"},{"key":"13042_CR33","doi-asserted-by":"crossref","unstructured":"Sahni T, Chandak C, Chedeti NR, Singh M (2017) Efficient Twitter sentiment classification using subjective distant supervision. In: International Conference on Communication Systems and Networks, pp 548\u2013553","DOI":"10.1109\/COMSNETS.2017.7945451"},{"key":"13042_CR34","unstructured":"Saif H, Fernandez M, He Y, Alani H (2013) Evaluation datasets for Twitter sentiment analysis: a survey and a new dataset, the sts-gold"},{"key":"13042_CR35","doi-asserted-by":"crossref","unstructured":"Singh TD, Singh TJ, Shadang M, Thokchom S (2021) Review comments of manipuri online video: Good, bad or ugly. In: International Conference on Computing and Communication Systems, vol 170. Springer, Shillong, p 45","DOI":"10.1007\/978-981-33-4084-8_5"},{"key":"13042_CR36","unstructured":"Tang G, Xia Y, Wang W, Lau R, Zheng F (2014) Clustering tweets using wikipedia concepts. In: Proceedings of the Language Resources and Evaluation Conference, Reykjavik, pp 2262\u20132267"},{"key":"13042_CR37","doi-asserted-by":"crossref","unstructured":"Teodorescu H-N, Saharia N (2015) An internet slang annotated dictionary and its use in assessing message attitude and sentiments. In: International Conference on Speech Technology and Human-Computer Dialogue. IEEE, Bucharest, pp 1\u20138","DOI":"10.1109\/SPED.2015.7343084"},{"key":"13042_CR38","doi-asserted-by":"publisher","unstructured":"Vosoughi S, Vijayaraghavan P, Roy D (2016) Tweet2vec: Learning tweet embeddings using character-level CNN-LSTM encoder-decoder. In: ACM SIGIR conference on Research and Development in Information Retrieval, pp 1041\u20131044, DOI https:\/\/doi.org\/10.1145\/2911451.2914762, (to appear in print)","DOI":"10.1145\/2911451.2914762"},{"key":"13042_CR39","doi-asserted-by":"crossref","unstructured":"Zhou D, Chen L, He Y (2015) An unsupervised framework of exploring events on Twitter: Filtering, extraction and categorization. In: AAAI conference on Artificial Intelligence, vol 29","DOI":"10.1609\/aaai.v29i1.9526"},{"key":"13042_CR40","unstructured":"Zou L, Song WW (2016) LDA-TM: A two-step approach to Twitter topic data clustering. In: International Conference on Cloud Computing and Big Data Analysis, pp 342\u2013347"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13042-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-13042-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13042-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T09:28:59Z","timestamp":1677058139000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-13042-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,6]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["13042"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-13042-4","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,5,6]]},"assertion":[{"value":"3 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2022","order":4,"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 that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}