{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:41:44Z","timestamp":1740109304320,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T00:00:00Z","timestamp":1563494400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T00:00:00Z","timestamp":1563494400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["TIN2015-71785-R"],"award-info":[{"award-number":["TIN2015-71785-R"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s10115-019-01383-w","type":"journal-article","created":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T16:02:34Z","timestamp":1563552154000},"page":"951-985","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Integrating learned and explicit document features for reputation monitoring in social media"],"prefix":"10.1007","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9161-0458","authenticated-orcid":false,"given":"Fernando","family":"Giner","sequence":"first","affiliation":[]},{"given":"Enrique","family":"Amig\u00f3","sequence":"additional","affiliation":[]},{"given":"Felisa","family":"Verdejo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,19]]},"reference":[{"key":"1383_CR1","unstructured":"Adhikari A, Singh S, Mondal D, Dutta B, Dutta A (2016) \u2018A Novel Information Theoretic Framework for Finding Semantic Similarity in WordNet\u2019, CoRR. In: Jajodia S (ed), arXiv preprint\u00a0 arXiv:1607.05422"},{"key":"1383_CR2","doi-asserted-by":"crossref","unstructured":"Amig\u00f3 E, Carrillo-de Albornoz J, Chugur I, Corujo A, Gonzalo J, Meij E, Rijke Md, Spina D (2014) Overview of RepLab 2014: author profiling and reputation dimensions for online reputation management. In: Proceedings of information access evaluation. Multilinguality, multimodality, and interaction\u20145th international conference of the CLEF initiative, CLEF 2014, Sheffield, UK, 15\u201318 September 2014","DOI":"10.1007\/978-3-319-11382-1_24"},{"key":"1383_CR3","first-page":"333","volume-title":"Lecture Notes in Computer Science","author":"Enrique Amig\u00f3","year":"2013","unstructured":"Amig\u00f3 E, de\u00a0Albornoz JC, Chugur I, Corujo A, Gonzalo J, Mart\u00edn-Wanton T, Meij E, de\u00a0Rijke M, Spina D (2013) Overview of RepLab 2013: evaluating online reputation monitoring systems. In: Proceedings of information access evaluation. 4th International conference of the CLEF initiative (CLEF 2013) multilinguality, multimodality, and visualization. Springer, Berlin, Heidelberg"},{"key":"1383_CR4","unstructured":"Amig\u00f3 E, Giner F, Gonzalo J, Verdejo F (2017a) An axiomatic account of similarity. In: Proceedings of the SIGIR\u201917 workshop on axiomatic thinking for information retrieval and related tasks (ATIR), SIGIR \u201920. ACM, New York, NY, USA"},{"key":"1383_CR5","first-page":"369","volume-title":"A formal and empirical study of unsupervised signal combination for textual similarity tasks","author":"E Amig\u00f3","year":"2017","unstructured":"Amig\u00f3 E, Giner F, Gonzalo J, Verdejo F (2017b) A formal and empirical study of unsupervised signal combination for textual similarity tasks. Springer, Cham, pp 369\u2013382"},{"key":"1383_CR6","doi-asserted-by":"crossref","unstructured":"Amig\u00f3 E, Giner F, Mizzaro S, Spina D (2018) A formal account on effectiveness evaluation and ranking fusion. In: Proceedings of the ACM SIGIR international conference on theory of information retrieval, ICTIR 2018, Tianjin, China, 14\u201317 September 2018","DOI":"10.1145\/3234944.3234958"},{"key":"1383_CR7","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1162\/tacl_a_00106","volume":"4","author":"S Arora","year":"2016","unstructured":"Arora S, Li Y, Liang Y, Ma T, Risteski A (2016) A latent variable model approach to PMI-based word embeddings. J Trans Assoc Comput Linguist (TACL) 4:385\u2013399","journal-title":"J Trans Assoc Comput Linguist (TACL)"},{"key":"1383_CR8","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI, Lafferty J (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"key":"1383_CR9","unstructured":"Brigadir I, Greene D, Cunningham P (2014) Adaptive representations for tracking breaking news on Twitter, arXiv preprint\u00a0 arXiv:1403.2923"},{"issue":"3","key":"1383_CR10","doi-asserted-by":"publisher","first-page":"510","DOI":"10.3758\/BF03193020","volume":"39","author":"A Bullinaria John","year":"2007","unstructured":"Bullinaria John A, Levy JP (2007) Extracting semantic representations from word co-occurrence statistics: a computational study. Behav Res Methods 39(3):510\u2013526","journal-title":"Behav Res Methods"},{"key":"1383_CR11","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1017\/S1351324900000139","volume":"1","author":"KW Church","year":"1995","unstructured":"Church KW, Gale WA (1995) Poisson mixtures. Nat Lang Eng 1:163\u2013190","journal-title":"Nat Lang Eng"},{"issue":"1","key":"1383_CR12","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/BF01014019","volume":"3","author":"V Cross","year":"1994","unstructured":"Cross V (1994) Fuzzy information retrieval. J Intell Inf Syst 3(1):29\u201356","journal-title":"J Intell Inf Syst"},{"key":"1383_CR13","doi-asserted-by":"crossref","unstructured":"Dagan I, Pereira F, Lee L (1994) Similarity-based estimation of word cooccurrence probabilities. In: In proceedings of the 32nd annual meeting of the association for computational linguistics, association for computational linguistics, pp\u00a0272\u2013278","DOI":"10.3115\/981732.981770"},{"issue":"4","key":"1383_CR14","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/S0019-9958(72)90199-4","volume":"20","author":"A De Luca","year":"1972","unstructured":"De Luca A, Termini S (1972) A definition of a nonprobabilistic entropy in the setting of fuzzy sets theory. Inf Control 20(4):301\u2013312","journal-title":"Inf Control"},{"key":"1383_CR15","unstructured":"Delgado M, Mart\u00edn-Bautista M, S\u00e1nchez D, Vila M (2001) Aggregating opinions in an information retrieval problem. In: Proceedings of EUROFUSE workshop on preference modelling and applications, Granada, Spain, pp\u00a0169\u2013173"},{"key":"1383_CR16","doi-asserted-by":"crossref","unstructured":"Djuric N, Wu H, Radosavljevic V, Grbovic M, Bhamidipati N (2015) Hierarchical neural language models for joint representation of streaming documents and their content. In: Proceedings of the 24th international conference on world wide web, international world wide web conferences steering committee, pp\u00a0248\u2013255","DOI":"10.1145\/2736277.2741643"},{"issue":"3","key":"1383_CR17","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1145\/352595.352597","volume":"18","author":"WR Greiff","year":"2000","unstructured":"Greiff WR, Ponte JM (2000) The maximum entropy approach and probabilistic IR models. ACM Trans Inf Syst (TOIS) 18(3):246\u2013287","journal-title":"ACM Trans Inf Syst (TOIS)"},{"issue":"4","key":"1383_CR18","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1002\/asi.4630260504","volume":"26","author":"SP Harter","year":"1975","unstructured":"Harter SP (1975) A probabilistic approach to automatic keyword indexing. Part II: an algorithm for probabilistc indexing. J Am Soc Inf Sci 26(4):280\u2013289","journal-title":"J Am Soc Inf Sci"},{"key":"1383_CR19","unstructured":"Herrera F, Herrera-Viedma E, Mart\u00ednez L (2002) An information retrieval system with unbalanced linguistic information based on the linguistic 2-tuple model. In: 8th International conference on information processing and management of uncertainty in knowledge-bases systems (IPMU2002). Wiley Online Library, Annecy (France), vol\u00a052, pp\u00a023\u201329"},{"key":"1383_CR20","unstructured":"Jiao Y, Cornec M, Jakubowicz J (2015) An entropy-based term weighting scheme and its application in e-commerce search engines. In: International symposium on web algorithms"},{"key":"1383_CR21","volume-title":"Introduction to the theory of fuzzy subsets","author":"A Kaufmann","year":"1975","unstructured":"Kaufmann A (1975) Introduction to the theory of fuzzy subsets, vol 2. Academic Press, Cambridge"},{"key":"1383_CR22","doi-asserted-by":"crossref","unstructured":"Ke W (2013) Information-theoretic term weighting schemes for document clustering. In: Proceedings of the 13th ACM\/IEEE-CS joint conference on digital libraries, ACM, pp\u00a0143\u2013152","DOI":"10.1145\/2467696.2467698"},{"key":"1383_CR23","unstructured":"Kohlas J (2017) Algebras of information. A new and extended axiomatic foundation, arXiv preprint\u00a0 arXiv:1701.02658"},{"key":"1383_CR24","first-page":"95","volume-title":"In formal theories of information. Wiley encyclopedia of computer science and engineering","author":"J Kohlas","year":"2008","unstructured":"Kohlas J, Pouly M, Schneuwly C (2008) Information algebra. In: Wah B (ed) In formal theories of information. Wiley encyclopedia of computer science and engineering. Wiley, Berlin, pp 95\u2013127"},{"issue":"2\u20133","key":"1383_CR25","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1080\/03081079008935108","volume":"17","author":"B Kosko","year":"1990","unstructured":"Kosko B (1990) Fuzziness vs. probability. Int J Gen Syst 17(2\u20133):211\u2013240","journal-title":"Int J Gen Syst"},{"issue":"1","key":"1383_CR26","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1109\/TIT.1978.1055832","volume":"24","author":"AV Lazo","year":"2006","unstructured":"Lazo AV, Rathie P (2006) On the entropy of continuous probability distributions (Corresp.). IEEE Trans Inf Theory 24(1):120\u2013122","journal-title":"IEEE Trans Inf Theory"},{"key":"1383_CR27","unstructured":"Levy O, Goldberg Y (2014) Neural word embedding as implicit matrix factorization. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds) Advances in neural information processing systems 27. Curran Associates, Inc., pp\u00a02177\u20132185"},{"key":"1383_CR28","unstructured":"Lin D (1998) An information-theoretic definition of similarity. In: Proceedings of the 15th international conference on machine learning, ICML \u201998. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp\u00a0296\u2013304"},{"key":"1383_CR29","unstructured":"Ma J, Gao W, Mitra P, Kwon S, Jansen BJ, Wong K-F, Cha M (2016) Detecting rumors from microblogs with recurrent neural networks. In: International joint conferences on artificial intelligence (IJCAI). Elsevier, pp\u00a03818\u20133824"},{"key":"1383_CR30","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Conference proceedings of the advances in neural information processing systems. Journal CoRR, vol. abs\/1310.4546"},{"key":"1383_CR31","unstructured":"Nie\u00dfen S, Och FJ, Leusch G, Ney H (2000) An evaluation tool for machine translation: fast evaluation for MT research. In: Proceedings of the 2nd international conference on language resources and evaluation (LREC). European Languages Resources Association (ELRA)"},{"key":"1383_CR32","unstructured":"Papineni K (2001) Why inverse document frequency?, In: Proceedings of the second meeting of the North American chapter of the association for computational linguistics on language technologies, NAACL \u201901. Association for Computational Linguistics, Stroudsburg, PA, USA, pp\u00a01\u20138"},{"key":"1383_CR33","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics, Doha, Qatar, pp\u00a01532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"1383_CR34","unstructured":"Resnik P (1995) Using information content to evaluate semantic similarity in a taxonomy. In: Proceedings of the 14th international joint conference on artificial intelligence, vol 1, IJCAI\u201995. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp\u00a0448\u2013453"},{"key":"1383_CR35","unstructured":"RI (2018) Why RI? Business through data-driven reputation management. https:\/\/www.reputationinstitute.com\/why-ri . Accessed 21 July 2018"},{"issue":"5","key":"1383_CR36","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1108\/00220410410560582","volume":"60","author":"S Robertson","year":"2004","unstructured":"Robertson S (2004) Understanding inverse document frequency: on theoretical arguments for IDF. J Doc 60(5):503\u2013520","journal-title":"J Doc"},{"key":"1383_CR37","unstructured":"Robertson SE, van Rijsbergen CJ, Porter MF (1981) Probabilistic models of indexing and searching. In: Proceedings of the 3rd annual ACM conference on research and development in information retrieval, SIGIR \u201980. Butterworth & Co., Kent, UK, UK, pp\u00a035\u201356"},{"issue":"1","key":"1383_CR38","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/91.660806","volume":"6","author":"IJ Rudas","year":"1998","unstructured":"Rudas IJ, Kaynak MO (1998) Entropy-based operations on fuzzy sets. J IEEE Trans Fuzzy Syst 6(1):33\u201340","journal-title":"J IEEE Trans Fuzzy Syst"},{"key":"1383_CR39","doi-asserted-by":"crossref","unstructured":"Shi Y, Wiggers P, Jonker CM (2012) Towards recurrent neural networks language models with linguistic and contextual features. In: 13th Annual conference of the international speech communication association, ISCA, pp\u00a01664\u20131667","DOI":"10.21437\/Interspeech.2012-456"},{"issue":"1","key":"1383_CR40","doi-asserted-by":"publisher","first-page":"5:1","DOI":"10.1145\/3052775","volume":"36","author":"M Shirakawa","year":"2017","unstructured":"Shirakawa M, Hara T, Nishio S (2017) IDF for word n-grams. ACM Trans Inf Syst (TOIS) 36(1):5:1\u20135:38","journal-title":"ACM Trans Inf Syst (TOIS)"},{"key":"1383_CR41","doi-asserted-by":"crossref","unstructured":"Tillmann C, Vogel S, Ney H, Zubiaga A, Sawaf H (1997) Accelerated DP based search for statistical translation. In: Proceedings of European conference on speech communication and technology","DOI":"10.21437\/Eurospeech.1997-673"},{"issue":"1","key":"1383_CR42","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.csl.2014.10.002","volume":"32","author":"A Toral","year":"2015","unstructured":"Toral A, Pecina P, Wang L, van Genabith J (2015) Linguistically-augmented perplexity-based data selection for language models. Hybrid machine translation: integration of linguistics and statistics. Comput Speech Lang 32(1):11\u201326","journal-title":"Comput Speech Lang"},{"key":"1383_CR43","doi-asserted-by":"crossref","unstructured":"Vakulenko S, Nixon L, Lupu M (2017) Character-based neural embeddings for tweet clustering. arXiv preprint\u00a0 arXiv:1703.05123","DOI":"10.18653\/v1\/W17-1105"},{"key":"1383_CR44","doi-asserted-by":"crossref","unstructured":"Wang X, McCallum A (2006) Topics over time: a non-markov continuous-time model of topical trends, In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, KDD \u201906, ACM, New York, NY, USA, pp\u00a0424\u2013433","DOI":"10.1145\/1150402.1150450"},{"key":"1383_CR45","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2016","unstructured":"Witten IH, Frank E, Hall MA, Pal CJ (2016) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, Burlington"},{"key":"1383_CR46","doi-asserted-by":"crossref","unstructured":"Yin J, Wang J (2014) A Dirichlet multinomial mixture model-based approach for short text clustering. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, pp\u00a0233\u2013242","DOI":"10.1145\/2623330.2623715"},{"issue":"2","key":"1383_CR47","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1016\/0022-247X(68)90078-4","volume":"23","author":"LA Zadeh","year":"1968","unstructured":"Zadeh LA (1968) Probability measures of fuzzy events. J Math Anal Appl 23(2):421\u2013427","journal-title":"J Math Anal Appl"},{"issue":"3","key":"1383_CR48","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1561\/1500000008","volume":"2","author":"C Zhai","year":"2008","unstructured":"Zhai C (2008) Statistical language models for information retrieval: a critical review. Found Trends Inf Retr 2(3):137\u2013213","journal-title":"Found Trends Inf Retr"},{"key":"1383_CR49","first-page":"338","volume-title":"Lecture Notes in Computer Science","author":"Wayne Xin Zhao","year":"2011","unstructured":"Zhao WX, Jiang J, Weng J, He J, Lim E-P, Yan H, Li X (2011) Comparing Twitter and traditional media using topic models. In: European conference on information retrieval. Springer, Heidelberg, pp 338\u2013349"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-019-01383-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-019-01383-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-019-01383-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T08:00:07Z","timestamp":1664006407000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-019-01383-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,19]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["1383"],"URL":"https:\/\/doi.org\/10.1007\/s10115-019-01383-w","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2019,7,19]]},"assertion":[{"value":"16 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}