[u' @incollection{sixto_analysis_2018, series = {Lecture {Notes} in {Computer} {Science}}, title = {Analysis of the {Structured} {Information} for {Subjectivity} {Detection} in {Twitter}}, isbn = {978-3-319-90286-9 978-3-319-90287-6}, url = {https://link.springer.com/chapter/10.1007/978-3-319-90287-6_9}, abstract = {In this paper, we analyze the opportunities of the structured information of the social networks for the subjectivity detection on Twitter micro texts. The sentiment analysis on Twitter has been usually performed through the automatic processing of the texts. However, the established limit of 140 characters and the particular characteristics of the texts reduce drastically the accuracy of Natural Language Processing (NLP) techniques when compared with other domains. Under these circumstances, it becomes necessary to study new data sources that allow us to extract new useful knowledge to represent and classify the texts. The structured information, also called meta-information or meta-data, provide us with alternative features of the texts that can improve the classification tasks. In this paper we analyze the features of the structured information and their usefulness in the opinion mining sub-domain, specially in the subjectivity detection task. Also present a novel classification of these features according to their origin.}, language = {en}, urldate = {2018-04-26}, booktitle = {Transactions on {Computational} {Collective} {Intelligence} {XXIX}}, publisher = {Springer, Cham}, author = {Sixto, Juan and Almeida, Aitor and L\xf3pez-de-Ipi\xf1a, Diego}, year = {2018}, doi = {10.1007/978-3-319-90287-6_9}, keywords = {Artificial Intelligence, ISI, NLP, Natural language processing, Sentiment analysis, Subjectivity detection, Text categorization, Twitter, e-rmp, ensemble, ensemble learning, machine learning, social network analysis, social networks, svn}, pages = {163--181}, } ']

[u' @incollection{sixto_approach_2016, series = {Lecture {Notes} in {Computer} {Science}}, title = {An {Approach} to {Subjectivity} {Detection} on {Twitter} {Using} the {Structured} {Information}}, copyright = {\xa92016 Springer International Publishing Switzerland}, isbn = {978-3-319-45242-5 978-3-319-45243-2}, url = {http://link.springer.com/chapter/10.1007/978-3-319-45243-2_11}, abstract = {In this paper, we propose an approach to the subjectivity detection on Twitter micro texts that explores the uses of the structured information of the social network framework. The sentiment analysis on Twitter has been usually performed through the automatic processing of the texts. However, the established limit of 140 characters and the particular characteristics of the texts reduce drastically the accuracy of Natural Language Processing (NLP) techniques. Under these circumstances, it becomes necessary to study new data sources that allow us to extract new useful knowledge to represent and classify the texts. The structured information, also called meta-information or meta-data, provide us with alternative features of the texts that can improve the classification tasks. In this study we have analysed the use of features extracted from the structured information in the subjectivity detection task, as a first step of the polarity detection task, and their integration with classical features.}, language = {en}, number = {9875}, urldate = {2016-09-22}, booktitle = {Computational {Collective} {Intelligence}}, publisher = {Springer International Publishing}, author = {Sixto, Juan and Almeida, Aitor and L\xf3pez-de-Ipi\xf1a, Diego}, editor = {Nguyen, Ngoc-Thanh and Iliadis, Lazaros and Manolopoulos, Yannis and Trawi\u0144ski, Bogdan}, month = sep, year = {2016}, doi = {10.1007/978-3-319-45243-2_11}, note = {00000 }, keywords = {Artificial Intelligence, Data analysis, Data mining for social networks, NLP, Natural language processing, Sentiment analysis, Social networks, Subjectivity detection, Text categorization, core-c, data mining, machine learning, opinion mining, twitter}, pages = {121--130}, } ']

[u' @incollection{sixto_improving_2016, series = {Lecture {Notes} in {Computer} {Science}}, title = {Improving the {Sentiment} {Analysis} {Process} of {Spanish} {Tweets} with {BM25}}, copyright = {\xa92016 Springer International Publishing Switzerland}, isbn = {978-3-319-41753-0 978-3-319-41754-7}, url = {http://link.springer.com/chapter/10.1007/978-3-319-41754-7_26}, abstract = {The enormous growth of user-generated information of social networks has caused the need for new algorithms and methods for their classification. The Sentiment Analysis (SA) methods attempt to identify the polarity of a text, using among other resources, the ranking algorithms. One of the most popular ranking algorithms is the Okapi BM25 ranking, designed to rank documents according to their relevance on a topic. In this paper, we present an approach of sentiment analysis for Spanish Tweets based combining the BM25 ranking function with a Linear Support Vector supervised model. We describe the implemented procedure to adapt BM25 to the peculiarities of SA in Twitter. The results confirm the potential of the BM25 algorithm to improve the sentiment analysis tasks.}, language = {en}, number = {9612}, urldate = {2016-06-21}, booktitle = {Natural {Language} {Processing} and {Information} {Systems}}, publisher = {Springer International Publishing}, author = {Sixto, Juan and Almeida, Aitor and L\xf3pez-de-Ipi\xf1a, Diego}, editor = {M\xe9tais, Elisabeth and Meziane, Farid and Saraee, Mohamad and Sugumaran, Vijayan and Vadera, Sunil}, month = jun, year = {2016}, doi = {10.1007/978-3-319-41754-7_26}, note = {00000 }, keywords = {Artificial Intelligence, BM25, Data analysis, Linear support vector, NLP, Natural language processing, Sentiment analysis, Term frequency, Twitter, core-c, machine learning, q1, social networks}, pages = {285--291}, } ']

[u' @inproceedings{sixto_deustotech_2015, title = {{DeustoTech} {Internet} at {TASS} 2015: {Sentiment} analysis and polarity classification in spanish tweets}, shorttitle = {{DeustoTech} {Internet} at {TASS} 2015}, url = {http://ceur-ws.org/Vol-1397/deusto.pdf}, abstract = {This article describes our system presented at the workshop for sentiment analysis TASS 2015. Our system approaches the task 1 of the workshop, which consists on performing an automatic sentiment analysis to determine the global polarity of a set of tweets in Spanish. To do this, our system is based on a model supervised Linear Support Vector Machines combined with some polarity lexicons. The influence of the different linguistic features and the different sizes of n-grams in improving algorithm performance. Also the results obtained, the various tests that have been conducted, and a discussion of the results are presented.}, urldate = {2015-09-22}, booktitle = {Proceedings of the {Annual} {Conference} of the {Spanish} {Society} for {Natural} {Language} {Processing} ({SEPLN}) 2015}, author = {Sixto, Juan and Almeida, Aitor and Lopez de Ipina, Diego}, month = oct, year = {2015}, note = {00000}, keywords = {Artificial Intelligence, Data analysis, NLP, Natural language processing, Polarity Classification, Sentiment analysis, Support Vector Machines, Twitter, machine learning, social networks}, pages = {23}, } ']

[u' @inproceedings{sixto_enable_2013, address = {Coventry, UK}, title = {Enable tweet-geolocation and don\u2019t drive {ERTs} crazy! {Improving} situational awareness using {Twitter}}, volume = {1}, abstract = {When traditional communication services are down during an emergency event, Twitter has proven to provide first-hand information to emergency response teams. The lack of geotagged tweets complicates these teams labour when trying to pin-point the events on a map. A rapid identification of situational awareness on incidents may help reduce the number of casualties and damages thanks to an efficient management. In this paper, we present a new approach to improve geolocation accuracy in Twitter posts, relying on NLP techniques and online geolocation APIs, providing the most trusted event location from a Twitter stream.}, author = {Sixto, Juan and Pe\xf1a, Oscar and Klein, Bernhard and Lopez-de-Ipina, Diego}, month = apr, year = {2013}, keywords = {Artificial Intelligence, Geolocation, Natural language processing, Situation awareness, Twitter, machine learning, sabess}, pages = {27--31}, } ']

[u' @incollection{sixto_analysing_2013, series = {Lecture {Notes} in {Computer} {Science}}, title = {Analysing {Customers} {Sentiments}: {An} {Approach} to {Opinion} {Mining} and {Classification} of {Online} {Hotel} {Reviews}}, copyright = {\xa92013 Springer-Verlag Berlin Heidelberg}, isbn = {978-3-642-38823-1 978-3-642-38824-8}, shorttitle = {Analysing {Customers} {Sentiments}}, url = {http://link.springer.com/chapter/10.1007/978-3-642-38824-8_38}, abstract = {Customer opinion holds a very important place in products and service business, especially for companies and potential customers. In the last years, opinions have become yet more important due to global Internet usage as opinions pool. Unfortunately , looking through customer reviews and extracting information to improve their service is a difficult work due to the large number of existing reviews. In this work we present a system designed to mine client opinions, classify them as positive or negative, and classify them according to the hotel features they belong to. To obtain this classification we use a machine learning classifier, reinforced with lexical resources to extract polarity and a specialized hotel features taxonomy.}, number = {7934}, urldate = {2013-09-18}, booktitle = {Natural {Language} {Processing} and {Information} {Systems}}, publisher = {Springer Berlin Heidelberg}, author = {Sixto, Juan and Almeida, Aitor and L\xf3pez-de-Ipi\xf1a, Diego}, editor = {M\xe9tais, Elisabeth and Meziane, Farid and Saraee, Mohamad and Sugumaran, Vijayan and Vadera, Sunil}, month = jan, year = {2013}, keywords = {Artificial Intelligence, Data analysis, ISI, NLP, Natural language processing, Social Data Mining, core-c, data mining, hotels, machine learning, opinion mining, thofu}, pages = {359--362}, } ']