Analyzing large-bodies of audiovisual information with respect to discoursepragmatic categories is a time-consuming, manual activity, yet of growing importance in a wide variety of domains. Given the transcription of the audiovisual recordings, we propose to model the task of assigning discoursepragmatic categories as supervised machine learning task. By analyzing the effects of a wide variety of feature classes, we can trace back the discoursepragmatic ratings to low-level language phenomena and better understand their dependency. The major contribution of this article is thus a rich feature set to analyze the relationship between the language and the discoursepragmatic categories assigned to an analyzed audiovisual unit. As one particular application of our methodology, we focus on modelling the quality of lessons according to a set of discourse-pragmatic dimensions. We examine multiple lesson quality dimensions relevant for educational researchers, e.g. to which extent teachers provide objective feedback, encourage cooperation and pursue thinking pathways of students. Using the transcripts of real classroom interactions recorded in Germany and Switzerland, we identify a wide range of lexical, stylistic and discourse-pragmatic phenomena, which affect the perception of lesson quality, and we interpret our findings together with the educational experts. Our results show that especially features focusing on discourse and cognitive processes are beneficial for this novel classification task, and that this task has a high potential for automated assistance.
{"title":"Document-level school lesson quality classification based on German transcripts","authors":"Lucie Flekova, Tahir Sousa, Margot Mieskes, Iryna Gurevych","doi":"10.21248/jlcl.30.2015.197","DOIUrl":"https://doi.org/10.21248/jlcl.30.2015.197","url":null,"abstract":"Analyzing large-bodies of audiovisual information with respect to discoursepragmatic categories is a time-consuming, manual activity, yet of growing importance in a wide variety of domains. Given the transcription of the audiovisual recordings, we propose to model the task of assigning discoursepragmatic categories as supervised machine learning task. By analyzing the effects of a wide variety of feature classes, we can trace back the discoursepragmatic ratings to low-level language phenomena and better understand their dependency. The major contribution of this article is thus a rich feature set to analyze the relationship between the language and the discoursepragmatic categories assigned to an analyzed audiovisual unit. As one particular application of our methodology, we focus on modelling the quality of lessons according to a set of discourse-pragmatic dimensions. We examine multiple lesson quality dimensions relevant for educational researchers, e.g. to which extent teachers provide objective feedback, encourage cooperation and pursue thinking pathways of students. Using the transcripts of real classroom interactions recorded in Germany and Switzerland, we identify a wide range of lexical, stylistic and discourse-pragmatic phenomena, which affect the perception of lesson quality, and we interpret our findings together with the educational experts. Our results show that especially features focusing on discourse and cognitive processes are beneficial for this novel classification task, and that this task has a high potential for automated assistance.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125566781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-01DOI: 10.21248/jlcl.30.2015.194
Alexander Magidow
This article describes a model for storing multiple forms of linguistic data within a relational database as developed and tested through a prototype database for storing data from Arabic dialects. A challenge that typically confronts linguistic documentation projects is the need for a flexible data model that can be adapted to the growing needs of a project (Dimitriadis, 2006). Contributors to linguistic databases typically cannot predict exactly which attributes of their data they will need to store, and therefore the initial design of the database may need to change over time. Many projects take advantage of the flexibility of XML and RDF to allow for continuing revisions to the data model. For some projects, there may be a compelling need to use a relational database system, though some approaches to relational database design may not flexible enough to allow for adaptation over time (Dimitriadis, 2006). The goal of this article is to describe a relational database model which can adapt easily to storing new data types as a project evolves. It both describes a general data model and shows its implementation within a working project. The model is primarily intended for storing discrete linguistic elements (phonemes, morphemes including general lexical data, sentences) as opposed to text corpora, and would be expected to store data on the order of thousands to hundreds of thousands of rows.1 The relational model described in this paper is centered around the linguistic datum, encoded as a string of characters, associated in a many-to-many relationship with ‘tags,’ and in many-to-many named relationships with other datums.2 For this reason, the model will be referred to as the ‘tag-and-relationship’ model. The combination of tags and relationships allows the database to store a wide variety of linguistic data. This data model was developed in tandem with a project to encode linguistic data from Arabic dialects (the “Database of Arabic Dialects”, DAD).3 Arabic is an extremely diverse language group, with a dialects stretching from Mauritania to Afghanistan,
{"title":"A relational database model and prototype for storing diverse discrete linguistic data","authors":"Alexander Magidow","doi":"10.21248/jlcl.30.2015.194","DOIUrl":"https://doi.org/10.21248/jlcl.30.2015.194","url":null,"abstract":"This article describes a model for storing multiple forms of linguistic data within a relational database as developed and tested through a prototype database for storing data from Arabic dialects. A challenge that typically confronts linguistic documentation projects is the need for a flexible data model that can be adapted to the growing needs of a project (Dimitriadis, 2006). Contributors to linguistic databases typically cannot predict exactly which attributes of their data they will need to store, and therefore the initial design of the database may need to change over time. Many projects take advantage of the flexibility of XML and RDF to allow for continuing revisions to the data model. For some projects, there may be a compelling need to use a relational database system, though some approaches to relational database design may not flexible enough to allow for adaptation over time (Dimitriadis, 2006). The goal of this article is to describe a relational database model which can adapt easily to storing new data types as a project evolves. It both describes a general data model and shows its implementation within a working project. The model is primarily intended for storing discrete linguistic elements (phonemes, morphemes including general lexical data, sentences) as opposed to text corpora, and would be expected to store data on the order of thousands to hundreds of thousands of rows.1 The relational model described in this paper is centered around the linguistic datum, encoded as a string of characters, associated in a many-to-many relationship with ‘tags,’ and in many-to-many named relationships with other datums.2 For this reason, the model will be referred to as the ‘tag-and-relationship’ model. The combination of tags and relationships allows the database to store a wide variety of linguistic data. This data model was developed in tandem with a project to encode linguistic data from Arabic dialects (the “Database of Arabic Dialects”, DAD).3 Arabic is an extremely diverse language group, with a dialects stretching from Mauritania to Afghanistan,","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"27 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113974572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-01DOI: 10.21248/jlcl.30.2015.196
Wladimir Sidorenko, A. Peldszus, Manfred Stede
This paper addresses the problem of segmenting German texts into minimal discourse units, as they are needed, for example, in RST-based discourse parsing. We discuss relevant variants of the problem, introduce the design of our annotation guidelines, and provide the results of an extensive interannotator agreement study of the corpus. Afterwards, we report on our experiments with three automatic classifiers that rely on the output of state-of-the-art parsers and use different amounts and kinds of syntactic knowledge: constituent parsing versus dependency parsing; tree-structure classification versus sequence labeling. Finally, we compare our approaches with the recent discourse segmentation methods proposed for English.
{"title":"Discourse Segmentation of German Texts","authors":"Wladimir Sidorenko, A. Peldszus, Manfred Stede","doi":"10.21248/jlcl.30.2015.196","DOIUrl":"https://doi.org/10.21248/jlcl.30.2015.196","url":null,"abstract":"This paper addresses the problem of segmenting German texts into minimal discourse units, as they are needed, for example, in RST-based discourse parsing. We discuss relevant variants of the problem, introduce the design of our annotation guidelines, and provide the results of an extensive interannotator agreement study of the corpus. Afterwards, we report on our experiments with three automatic classifiers that rely on the output of state-of-the-art parsers and use different amounts and kinds of syntactic knowledge: constituent parsing versus dependency parsing; tree-structure classification versus sequence labeling. Finally, we compare our approaches with the recent discourse segmentation methods proposed for English.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128065606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sentiment classification aims to determine whether the semantic orientation of a text is positive, negative or neutral. It can be tackled at several levels of granularity: expression or phrase level, sentence level, and document level. In the scope of this research, we are interested in the sentence and sub-sentential level classification which can provide very useful trends for information retrieval and extraction applications, Question Answering systems and summarization tasks. In the context of our work, we address the problem of Arabic sentiment classification at sub-sentential level by (i) building a high coverage sentiment lexicon with semi-automatic approach; (ii) creating a large multi-domain annotated sentiment corpus segmented into discourse segments in order to evaluate our sentiment approach; and (iii) applying a lexicon-based approach with an aggregation model taking into account advanced linguistic phenomena such as negation and intensification. The results that we obtained are considered good and close to state of the art results in English language.
{"title":"Sentiment Classification at Discourse Segment Level: Experiments on multi-domain Arabic corpus","authors":"Amine Bayoudhi, Hatem Ghorbel, Houssem Koubaa, Lamia Hadrich Belguith","doi":"10.21248/jlcl.30.2015.193","DOIUrl":"https://doi.org/10.21248/jlcl.30.2015.193","url":null,"abstract":"Sentiment classification aims to determine whether the semantic orientation of a text is positive, negative or neutral. It can be tackled at several levels of granularity: expression or phrase level, sentence level, and document level. In the scope of this research, we are interested in the sentence and sub-sentential level classification which can provide very useful trends for information retrieval and extraction applications, Question Answering systems and summarization tasks. In the context of our work, we address the problem of Arabic sentiment classification at sub-sentential level by (i) building a high coverage sentiment lexicon with semi-automatic approach; (ii) creating a large multi-domain annotated sentiment corpus segmented into discourse segments in order to evaluate our sentiment approach; and (iii) applying a lexicon-based approach with an aggregation model taking into account advanced linguistic phenomena such as negation and intensification. The results that we obtained are considered good and close to state of the art results in English language.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131315218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-01DOI: 10.21248/jlcl.29.2014.189
Eliza Margaretha, H. Lüngen
Wikipedia is a valuable resource, useful as a lingustic corpus or a dataset for many kinds of research. We built corpora from Wikipedia articles and talk pages in the I5 format, a TEI customisation used in the German Reference Corpus (Deutsches Referenzkorpus DeReKo). Our approach is a two-stage conversion combining parsing using the Sweble parser, and transformation using XSLT stylesheets. The conversion approach is able to successfully generate rich and valid corpora regardless of languages. We also introduce a method to segment user contributions in talk pages into postings.
{"title":"Building Linguistic Corpora from Wikipedia Articles and Discussions","authors":"Eliza Margaretha, H. Lüngen","doi":"10.21248/jlcl.29.2014.189","DOIUrl":"https://doi.org/10.21248/jlcl.29.2014.189","url":null,"abstract":"Wikipedia is a valuable resource, useful as a lingustic corpus or a dataset for many kinds of research. We built corpora from Wikipedia articles and talk pages in the I5 format, a TEI customisation used in the German Reference Corpus (Deutsches Referenzkorpus DeReKo). Our approach is a two-stage conversion combining parsing using the Sweble parser, and transformation using XSLT stylesheets. The conversion approach is able to successfully generate rich and valid corpora regardless of languages. We also introduce a method to segment user contributions in talk pages into postings.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"230 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124540041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-01DOI: 10.21248/jlcl.29.2014.182
Josef Ruppenhofer, Julia Maria Struß, J. Sonntag, Stefan Gindl
Accurate opinion mining requires the exact identification of the source and target of an opinion. To evaluate diverse tools, the research community relies on the existence of a gold standard corpus covering this need. Since such a corpus is currently not available for German, the Interest Group on German Sentiment Analysis decided to create such a resource and make it available to the research community in the context of a shared task. In this paper, we describe the selection of textual sources, development of annotation guidelines, and first evaluation results in the creation of a gold standard corpus for the German language.
{"title":"IGGSA-STEPS: Shared Task on Source and Target Extraction from Political Speeches","authors":"Josef Ruppenhofer, Julia Maria Struß, J. Sonntag, Stefan Gindl","doi":"10.21248/jlcl.29.2014.182","DOIUrl":"https://doi.org/10.21248/jlcl.29.2014.182","url":null,"abstract":"Accurate opinion mining requires the exact identification of the source and target of an opinion. To evaluate diverse tools, the research community relies on the existence of a gold standard corpus covering this need. Since such a corpus is currently not available for German, the Interest Group on German Sentiment Analysis decided to create such a resource and make it available to the research community in the context of a shared task. In this paper, we describe the selection of textual sources, development of annotation guidelines, and first evaluation results in the creation of a gold standard corpus for the German language.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122297917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-01DOI: 10.21248/jlcl.29.2014.190
W. Spooren, T. V. Charldorp
Present day access to a wealth of electronically available linguistic data creates enormous opportunities for cutting edge research questions and analyses. Computer-mediated communication (CMC) data are specifically interesting, for example because the multimodal character of new media puts our ideas about discourse issues like coherence to the test. At the same time CMC data are ephemeral, because of rapid changing technology. That is why we urgently need to collect CMC discourse data before the technology becomes obsolete. This paper describes a number of challenges we encountered when collecting a chat corpus with data from secondary school children in Amsterdam. These challenges are various in nature: logistic, ethical and technological.
{"title":"Challenges and experiences in collecting a chat corpus","authors":"W. Spooren, T. V. Charldorp","doi":"10.21248/jlcl.29.2014.190","DOIUrl":"https://doi.org/10.21248/jlcl.29.2014.190","url":null,"abstract":"Present day access to a wealth of electronically available linguistic data creates enormous opportunities for cutting edge research questions and analyses. Computer-mediated communication (CMC) data are specifically interesting, for example because the multimodal character of new media puts our ideas about discourse issues like coherence to the test. At the same time CMC data are ephemeral, because of rapid changing technology. That is why we\u0000urgently need to collect CMC discourse data before the technology becomes obsolete. This paper describes a number of challenges we encountered when collecting a chat corpus with data from secondary school children in Amsterdam. These challenges are various in nature: logistic, ethical and technological.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124118766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-01DOI: 10.21248/jlcl.29.2014.181
M. Marchand, Romaric Besançon, O. Mesnard, Anne Vilnat
Expression of opinion depends on the domain. For instance, some words, called here multi-polarity words, have dierent polarities across domain. Therefore, a classifier trained on one domain and tested on another one will not perform well without adaptation. This article presents a study of the influence of these multi-polarity words on domain adaptation for automatic opinion classification. We also suggest an exploratory method for detecting them without using any label in the target domain. We show as well how these multi-polarity words can improve opinion classification in an open-domain corpus.
{"title":"Domain Adaptation for Opinion Mining: A Study of Multipolarity Words","authors":"M. Marchand, Romaric Besançon, O. Mesnard, Anne Vilnat","doi":"10.21248/jlcl.29.2014.181","DOIUrl":"https://doi.org/10.21248/jlcl.29.2014.181","url":null,"abstract":"Expression of opinion depends on the domain. For instance, some words, called here multi-polarity words, have dierent polarities across domain. Therefore, a classifier trained on one domain and tested on another one will not perform well without adaptation. This article presents a study of the influence of these multi-polarity words on domain adaptation for automatic opinion classification. We also suggest an exploratory method for detecting them without using any label in the target domain. We show as well how these multi-polarity words can improve opinion classification in an open-domain corpus.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"225 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127615119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-01DOI: 10.21248/jlcl.29.2014.180
S. Albertini, Alessandro Zamberletti, I. Gallo
The rapid growth of Web information led to an increasing amount of user-generated content, such as customer reviews of products, forum posts and blogs. In this paper we face the task of assigning a sentiment polarity to user-generated short documents to determine whether each of them communicates a positive or negative judgment about a subject. The method we propose exploits a Growing Hierarchical SelfOrganizing Map to obtain a sparse encoding of user-generated content. The encoded documents are subsequently given as input to a Support Vector Machine classifier that assigns them a polarity label. Unlike other works on opinion mining, our model does not use a priori hypotheses involving special words, phrases or language constructs typical of certain domains. Using a dataset composed by customer reviews of products, the experimental results we obtain are close to those achieved by other recent works.
{"title":"Unsupervised feature learning for sentiment classification of short documents","authors":"S. Albertini, Alessandro Zamberletti, I. Gallo","doi":"10.21248/jlcl.29.2014.180","DOIUrl":"https://doi.org/10.21248/jlcl.29.2014.180","url":null,"abstract":"The rapid growth of Web information led to an increasing amount of user-generated content, such as customer reviews of products, forum posts and blogs. In this paper we face the task of assigning a sentiment polarity to user-generated short documents to determine whether each of them communicates a positive or negative judgment about a subject. The method we propose exploits a Growing Hierarchical SelfOrganizing Map to obtain a sparse encoding of user-generated content. The encoded documents are subsequently given as input to a Support Vector Machine classifier that assigns them a polarity label. Unlike other works on opinion mining, our model does not use a priori hypotheses involving special words, phrases or language constructs typical of certain domains. Using a dataset composed by customer reviews of products, the experimental results we obtain are close to those achieved by other recent works.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"38 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120997579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-01DOI: 10.21248/jlcl.29.2014.185
Yuqiao Gu, Fabio Celli, J. Steinberger, A. Anderson, Massimo Poesio, C. Strapparava, B. Murphy
We present the results of exploratory experiments using lexical valence extracted from brain using electroencephalography (EEG) for sentiment analysis. We selected 78 English words (36 for training and 42 for testing), presented as stimuli to 3 English native speakers. EEG signals were recorded from the subjects while they performed a mental imaging task for each word stimulus. Wavelet decomposition was employed to extract EEG features from the time-frequency domain. The extracted features were used as inputs to a sparse multinomial logistic regression (SMLR) classifier for valence classification, after univariate ANOVA feature selection. After mapping EEG signals to sentiment valences, we exploited the lexical polarity extracted from brain data for the prediction of the valence of 12 sentences taken from the SemEval-2007 shared task, and compared it against existing lexical resources.
{"title":"Using Brain Data for Sentiment Analysis","authors":"Yuqiao Gu, Fabio Celli, J. Steinberger, A. Anderson, Massimo Poesio, C. Strapparava, B. Murphy","doi":"10.21248/jlcl.29.2014.185","DOIUrl":"https://doi.org/10.21248/jlcl.29.2014.185","url":null,"abstract":"We present the results of exploratory experiments using lexical valence extracted from brain using electroencephalography (EEG) for sentiment analysis. We selected 78 English words (36 for training and 42 for testing), presented as stimuli to 3 English native speakers. EEG signals were recorded from the subjects while they performed a mental imaging task for each word stimulus. Wavelet decomposition was employed to extract EEG features from the time-frequency domain. The extracted features were used as inputs to a sparse multinomial logistic regression (SMLR) classifier for valence classification, after univariate ANOVA feature selection. After mapping EEG signals to sentiment valences, we exploited the lexical polarity extracted from brain data for the prediction of the valence of 12 sentences taken from the SemEval-2007 shared task, and compared it against existing lexical resources.","PeriodicalId":402489,"journal":{"name":"J. Lang. Technol. Comput. Linguistics","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128562641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：