{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:11:32Z","timestamp":1788239492104,"version":"build-2803163510"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,2,11]],"date-time":"2021-02-11T00:00:00Z","timestamp":1613001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,2,11]],"date-time":"2021-02-11T00:00:00Z","timestamp":1613001600000},"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":["Cogn Comput"],"published-print":{"date-parts":[[2022,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Financial investors make trades based on available information. Previous research has proved that microblogs are a useful source for supporting stock market decisions. However, the financial domain lacks specific sentiment lexicons that could be utilized to extract the sentiment from these microblogs. In this research, we investigate automatic approaches that can be used to build financial sentiment lexicons. We introduce weighted versions of the Pointwise Mutual Information approaches to build sentiment lexicons automatically. Furthermore, existing sentiment lexicons often neglect negation while building the sentiment lexicons. In this research, we also propose two methods (Negated Word and Flip Sentiment) to extend the sentiment building approaches to take into account negation when constructing a sentiment lexicon. We build the financial sentiment lexicons by leveraging 200,000 messages from StockTwits. We evaluate the constructed financial sentiment lexicons in two different sentiment classification tasks (unsupervised and supervised). In addition, the created financial sentiment lexicons are compared with each other and with other existing sentiment lexicons. The best performing financial sentiment lexicon is built by combining our Weighted Normalized Pointwise Mutual Information approach with the Negated Word approach. It outperforms all the other sentiment lexicons in the two sentiment classification tasks. In the unsupervised sentiment classification task, it has, on average, a balanced accuracy of 69.4%, and in the supervised setting, a balanced accuracy of 75.1%. Moreover, the various sentiment classification tasks confirm that the sentiment lexicons could be improved by taking into account negation while building the sentiment lexicons. The improvement could be made by using one of the proposed methods to incorporate negation in the sentiment lexicon construction process.<\/jats:p>","DOI":"10.1007\/s12559-021-09833-w","type":"journal-article","created":{"date-parts":[[2021,2,11]],"date-time":"2021-02-11T23:52:31Z","timestamp":1613087551000},"page":"442-460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Automatically Building Financial Sentiment Lexicons While Accounting for Negation"],"prefix":"10.1007","volume":"14","author":[{"given":"Thomas","family":"Bos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8031-758X","authenticated-orcid":false,"given":"Flavius","family":"Frasincar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,11]]},"reference":[{"key":"9833_CR1","doi-asserted-by":"crossref","unstructured":"Liu B. Sentiment analysis: mining opinions, sentiments, and emotions. Cambridge University Press; 2015.","DOI":"10.1017\/CBO9781139084789"},{"key":"9833_CR2","doi-asserted-by":"crossref","unstructured":"Hu M, Liu B. Mining and summarizing customer reviews. In: 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD 2004. p. 168\u2013177.","DOI":"10.1145\/1014052.1014073"},{"key":"9833_CR3","doi-asserted-by":"crossref","unstructured":"Cambria E, Hussain A, Havasi C, Eckl C. Sentic computing: exploitation of common sense for the development of emotion-sensitive systems. Development of Multimodal Interfaces: Active Listening, and Synchrony, Lecture Notes in Computer Science.\u00a0Springer, Cambria, Erik and Li, Yang and Xing. Soujanya and Kwok, Kenneth: Frank Z. and Poria. 2010. vol. 5967, p. 148\u2013156.","DOI":"10.1007\/978-3-642-12397-9_12"},{"key":"9833_CR4","doi-asserted-by":"crossref","unstructured":"Feldman R. Techniques and applications for sentiment analysis. In: Communications of the ACM. 2013. vol.\u00a056, p. 82\u201389.","DOI":"10.1145\/2436256.2436274"},{"key":"9833_CR5","doi-asserted-by":"crossref","unstructured":"Bollen J, Mao H, Zeng X. Twitter mood predicts the stock market. In: Journal of Computational Science.\u00a0Elsevier 2011.\u00a0vol.\u00a02, p. 1\u20138.","DOI":"10.1016\/j.jocs.2010.12.007"},{"key":"9833_CR6","doi-asserted-by":"crossref","unstructured":"Montoyo A, Mart\u00edNez-Barco P, Balahur A. Subjectivity and sentiment analysis: an overview of the current state of the area and envisaged developments. In: Decis Support Syst.\u00a0 Elsevier 2012.\u00a0vol. 53 (4), p. 675\u2013679.","DOI":"10.1016\/j.dss.2012.05.022"},{"issue":"1","key":"9833_CR7","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1007\/s10462-017-9588-9","volume":"50","author":"FZ Xing","year":"2018","unstructured":"Xing FZ, Cambria E, Welsch RE. Natural language based financial forecasting: a survey. Artif Intell Rev. 2018;50(1):49\u201373.","journal-title":"Artif Intell Rev"},{"issue":"6","key":"9833_CR8","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.1007\/s12559-018-9609-2","volume":"10","author":"L Malandri","year":"2018","unstructured":"Malandri L, Xing FZ, Orsenigo C, Vercellis C, Cambria E. Public mood-driven asset allocation: the importance of financial sentiment in portfolio management. Cogn Comput. 2018;10(6):1167\u201376.","journal-title":"Cogn Comput"},{"key":"9833_CR9","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1109\/MCI.2018.2866727","volume":"13","author":"FZ Xing","year":"2018","unstructured":"Xing FZ, Cambria E, Welsch RE. Intelligent asset allocation via market sentiment views. IEEE Comput Intell Mag. 2018;13:25\u201334.","journal-title":"IEEE Comput Intell Mag"},{"key":"9833_CR10","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.eswa.2019.06.014","volume":"135","author":"A Picasso","year":"2019","unstructured":"Picasso A, Merello S, Ma Y, Oneto L, Cambria E. Technical analysis and sentiment embeddings for market trend prediction. Expert Systems with Applications. 2019;135:60\u201370.","journal-title":"Expert Systems with Applications"},{"key":"9833_CR11","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.eswa.2018.06.016","volume":"112","author":"B Weng","year":"2018","unstructured":"Weng B, Lu L, Wang X, Megahed FM, Martinez W. Predicting short-term stock prices using ensemble methods and online data sources. Expert Systems with Applications. 2018;112:258\u201373.","journal-title":"Expert Systems with Applications"},{"key":"9833_CR12","doi-asserted-by":"crossref","unstructured":"Loughran T, McDonald B. When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. In: J Financ, vol.\u00a066, p. 35\u201365. Wiley Online Library (2011)","DOI":"10.1111\/j.1540-6261.2010.01625.x"},{"key":"9833_CR13","doi-asserted-by":"crossref","unstructured":"Oliveira N, Cortez P, Areal N. Automatic creation of stock market lexicons for sentiment analysis using stocktwits data. In: 18th International Database Engineering & Applications Symposium. ACM 2014. p. 115\u2013123.","DOI":"10.1145\/2628194.2628235"},{"key":"9833_CR14","doi-asserted-by":"crossref","unstructured":"Oliveira N, Cortez P, Areal N. Stock market sentiment lexicon acquisition using microblogging data and statistical measures. In: Decis Support Syst.\u00a0Elsevier 2016.\u00a0vol.\u00a085, p. 62\u201373.","DOI":"10.1016\/j.dss.2016.02.013"},{"key":"9833_CR15","doi-asserted-by":"crossref","unstructured":"Al-Twairesh N, Al-Khalifa H, AlSalman A. AraSenTi: Large-scale twitter-specific arabic sentiment lexicons. In: 54th Annual Meeting of the Association for Computational Linguistics ACL. 2016. vol.\u00a01, p. 697\u2013705.","DOI":"10.18653\/v1\/P16-1066"},{"key":"9833_CR16","doi-asserted-by":"crossref","unstructured":"Liu B. Sentiment analysis and opinion mining. Morgan & Claypool Publishers (2012)","DOI":"10.2200\/S00416ED1V01Y201204HLT016"},{"key":"9833_CR17","unstructured":"Stone PJ, Dunphy DC, Smith MS. The General Inquirer: a computer approach to content analysis, vol. 8. MIT Press; 1966."},{"key":"9833_CR18","doi-asserted-by":"crossref","unstructured":"Wilson T, Wiebe J, Hoffmann P. Recognizing contextual polarity in phrase-level sentiment analysis. In: Conference on Human Language Technology and Empirical Methods in Natural Language Processing. ACL 2005. p. 347\u2013354.","DOI":"10.3115\/1220575.1220619"},{"key":"9833_CR19","doi-asserted-by":"crossref","unstructured":"Jegadeesh N, Wu D. Word power: a new approach for content analysis. In: J Financ Econ.\u00a0Elsevier 2013.\u00a0vol. 110, p. 712\u2013729.","DOI":"10.1016\/j.jfineco.2013.08.018"},{"key":"9833_CR20","doi-asserted-by":"crossref","unstructured":"Heerschop B, Hogenboom A, Frasincar F. Sentiment lexicon creation from lexical resources. In: 14th International Conference on Business Information Systems (BIS 2011), Lecture Notes in Business Information Processing.\u00a0Springer 2011. vol.\u00a087, p. 185\u2013196.","DOI":"10.1007\/978-3-642-21863-7_16"},{"key":"9833_CR21","doi-asserted-by":"crossref","unstructured":"Miller GA. WordNet: a lexical database for english. In: Communications of the ACM. 1995. vol.\u00a038, p. 39\u201341.\u00a0","DOI":"10.1145\/219717.219748"},{"key":"9833_CR22","doi-asserted-by":"crossref","unstructured":"Turney PD. Thumbs up or thumbs down?: Semantic orientation applied to unsupervised classification of reviews. In: 40th Annual Meeting on Association for Computational Linguistics. ACL 2002. p. 417\u2013424.","DOI":"10.3115\/1073083.1073153"},{"key":"9833_CR23","doi-asserted-by":"crossref","unstructured":"Labille K, Alfarhood S, Gauch S. Estimating sentiment via probability and information theory. In: 8th International Conference on Knowledge Discovery and Information Retrieval KDIR.\u00a0SciTePress 2016. p. 121\u2013129.","DOI":"10.5220\/0006072101210129"},{"key":"9833_CR24","unstructured":"Labille K, Gauch S, Alfarhood S. Creating domain-specific sentiment lexicons via text mining. In: 6th KDD Workshop on Issues of Sentiment Discovery and Opinion Mining. WISDOM 2017."},{"key":"9833_CR25","doi-asserted-by":"crossref","unstructured":"Li Q, Shah S. Learning stock market sentiment lexicon and sentiment-oriented word vector from Stocktwits. In: 21st Conference on Computational Natural Language Learning. CoNLL 2017, p. 301\u2013310.","DOI":"10.18653\/v1\/K17-1031"},{"key":"9833_CR26","unstructured":"Tang D, Wei F, Qin B, Zhou M, Liu T. Building large-scale twitter-specific sentiment lexicon : a representation learning approach. In: 25th International Conference on Computational Linguistics. ACL 2014, p. 172\u2013182."},{"key":"9833_CR27","doi-asserted-by":"crossref","unstructured":"Wang L, Xia R. Sentiment lexicon construction with representation learning based on hierarchical sentiment supervision. In: 2017 Conference on Empirical Methods in Natural Language Processing. ACL 2017. p. 502\u2013510.","DOI":"10.18653\/v1\/D17-1052"},{"key":"9833_CR28","doi-asserted-by":"crossref","unstructured":"Vo DT, Zhang Y. Don\u2019t count, predict! An automatic approach to learning sentiment lexicons for short text. In: 54th Annual Meeting of the Association for Computational Linguistics. ACL 2016. vol.\u00a02, p. 219\u2013224.","DOI":"10.18653\/v1\/P16-2036"},{"issue":"3","key":"9833_CR29","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1016\/j.ipm.2018.11.002","volume":"56","author":"FZ Xing","year":"2019","unstructured":"Xing FZ, Pallucchini F, Cambria E. Cognitive-inspired domain adaptation of sentiment lexicons. Inf Process Manag. 2019;56(3):554\u201364.","journal-title":"Inf Process Manag"},{"key":"9833_CR30","doi-asserted-by":"crossref","unstructured":"Bayes T, Price R. An essay towards solving a problem in the doctrine of chances. by the late Rev. Mr. Bayes, communicated by Mr. Price, in a letter to John Canton, A. M. F. R. S. In: Philosophical Transactions of the Royal Society of London. 1763. vol.\u00a053, p. 370\u2013418.","DOI":"10.1098\/rstl.1763.0053"},{"key":"9833_CR31","doi-asserted-by":"crossref","unstructured":"Church KW, Hanks P. Word association norms, mutual information, and lexicography. In: 27th Annual Meeting on Association for Computational Linguistics. ACL. 1989. vol.\u00a016, p. 22\u201329.","DOI":"10.3115\/981623.981633"},{"key":"9833_CR32","doi-asserted-by":"crossref","unstructured":"Fano RM. Transmission of information: a statistical theory of communication. In: Am J Phys. MIT Press. 1961. vol.\u00a029, p. 793\u2013794.\u00a0","DOI":"10.1119\/1.1937609"},{"key":"9833_CR33","unstructured":"Bouma G. Normalized (pointwise) mutual information in collocation extraction. From Form to Meaning: Processing Texts Automatically. 2009. p. 31\u201340."},{"key":"9833_CR34","doi-asserted-by":"crossref","unstructured":"Salton G, Buckley C. Term-weighting approaches in automatic text retrieval. In: Inf Process Manag. Pergamon Press, Inc. 1988.\u00a0vol.\u00a024, p. 513\u2013523.","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"9833_CR35","first-page":"209","volume":"29","author":"D Wang","year":"2013","unstructured":"Wang D, Zhang H. Inverse-category-frequency based supervised term weighting schemes for text categorization. J Inf Sci Eng. 2013;29:209\u201325.","journal-title":"J Inf Sci Eng"},{"key":"9833_CR36","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1109\/TPAMI.2008.110","volume":"31","author":"M Lan","year":"2009","unstructured":"Lan M, Tan CL, Su J, Lu Y. Supervised and traditional term weighting methods for automatic text categorization. IEEE Trans Pattern Anal Mach Intell. 2009;31:721\u201335.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9833_CR37","unstructured":"Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. In: 1st International Conference on Learning Representations. ICLR 2013, p. 1\u201312."},{"key":"9833_CR38","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD. GloVe: Global vectors for word representation. In: 2014 Empirical Methods in Natural Language Processing. ACL 2014. p. 1532\u20131543.","DOI":"10.3115\/v1\/D14-1162"},{"key":"9833_CR39","doi-asserted-by":"crossref","unstructured":"Hogenboom A, Van\u00a0Iterson P, Heerschop B, Frasincar F, Kaymak U. Determining negation scope and strength in sentiment analysis. In: IEEE International Conference on Systems, Man, and Cybernetics. 2011. p. 2589\u20132594.","DOI":"10.1109\/ICSMC.2011.6084066"},{"key":"9833_CR40","doi-asserted-by":"crossref","unstructured":"Jia L, Yu C, Meng W. The effect of negation on sentiment analysis and retrieval effectiveness. In: 18th ACM Conference on Information and Knowledge Management. CIKM 2009. p. 1827\u20131830.","DOI":"10.1145\/1645953.1646241"},{"key":"9833_CR41","unstructured":"Councill IG, McDonald R, Velikovich L. What\u2019s great and what\u2019s not: learning to classify the scope of negation for improved sentiment analysis. In: Workshop on Negation and Speculation in Natural Language Processing. ACL. 2010. p. 51\u201359."},{"key":"9833_CR42","doi-asserted-by":"crossref","unstructured":"Morante R, Liekens A, Daelemans W. Learning the scope of negation in biomedical texts. In: 2008 Conference on Empirical Methods in Natural Language Processing. ACL\u00a02008. p. 715\u2013724.","DOI":"10.3115\/1613715.1613805"},{"key":"9833_CR43","unstructured":"Mohammad SM, Kiritchenko S, Zhu X. NRC-Canada: building the state-of-the-art in sentiment analysis of tweets. In: 7th International Workshop on Semantic Evaluation. ACL. 2013."},{"key":"9833_CR44","doi-asserted-by":"crossref","unstructured":"Hutto CJ, Gilbert E. VADER: A parsimonious rule-based model for sentiment analysis of social media text. In: 8th International AAAI Conference on Weblogs and Social Media. ICWSM 2014. p. 216\u2013225.\u00a0","DOI":"10.1609\/icwsm.v8i1.14550"},{"key":"9833_CR45","doi-asserted-by":"crossref","unstructured":"Cambria E, Li Y, Xing FZ, Poria S, Kwok K. SenticNet 6: ensemble application of symbolic and subsymbolic AI for sentiment analysis. In: 29th ACM International Conference on Information & Knowledge Management. ACM CIKM. 2020. p. 105\u2013114.","DOI":"10.1145\/3340531.3412003"},{"key":"9833_CR46","doi-asserted-by":"crossref","unstructured":"Zhu X, Kiritchenko S, Mohammad S. NRC-Canada-2014: recent improvements in the sentiment analysis of tweets. In: 8th International Workshop on Semantic Evaluation. ACL 2014. p. 443\u2013447.","DOI":"10.3115\/v1\/S14-2077"},{"key":"9833_CR47","unstructured":"Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ. LibLineaR: a library for large linear classification. In: J Mach Learn Res.\u00a0JMLR.org. 2008.\u00a0vol.\u00a09, p. 1871\u20131874."},{"key":"9833_CR48","doi-asserted-by":"crossref","unstructured":"Cortis K, Freitas A, Daudert T, Huerlimann M, Zarrouk M, Handschuh S, Davis B. SemEval-2017 task 5: fine-grained sentiment analysis on financial microblogs and news. In: 11th International Workshop on Semantic Evaluation. ACL. 2017.\u00a0p. 519\u2013535.","DOI":"10.18653\/v1\/S17-2089"},{"key":"9833_CR49","doi-asserted-by":"crossref","unstructured":"Kwartler T. Text mining in practice with R. John Wiley & Sons; 2017.","DOI":"10.1002\/9781119282105"},{"issue":"5","key":"9833_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v025.i05","volume":"25","author":"I Feinerer","year":"2008","unstructured":"Feinerer I, Hornik K, Meyer D. Text mining infrastructure in R. J Stat Softw. 2008;25(5):1\u201354.","journal-title":"J Stat Softw"},{"key":"9833_CR51","unstructured":"Go A, Bhayani R, Huang L. Twitter sentiment classification using distant supervision. In: Final Projects from CS224N for Spring 2008\/2009 at the Stanford Natural Language Processing Group.\u00a0Stanford University 2009.\u00a0p. 1\u20136."},{"key":"9833_CR52","unstructured":"Hogenboom A, Bal D, Frasincar F, Bal M, De\u00a0Jong F. Kaymak U. Exploiting emoticons in polarity classification of text. In: Journal of Web Engineering (JWE).\u00a0Rinton Press 2015,\u00a0vol. 14 (1 & 2), p. 22\u201340."},{"key":"9833_CR53","doi-asserted-by":"crossref","unstructured":"Hogenboom A, Bal D, Frasincar F, Bal M, de\u00a0Jong F, Kaymak U. Exploiting emoticons in sentiment analysis. In: 28th Symposium on Applied Computing. SAC 2013, p. 703\u2013710.","DOI":"10.1145\/2480362.2480498"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-021-09833-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-021-09833-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-021-09833-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T17:32:29Z","timestamp":1671211949000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-021-09833-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,11]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["9833"],"URL":"https:\/\/doi.org\/10.1007\/s12559-021-09833-w","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,11]]},"assertion":[{"value":"18 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2021","order":3,"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 they have no conflict of interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}]}}