Vocabulary is very important in English language teaching but often ignored in learning activities. It is difficult for EFL learners to learn English with a lack of vocabulary. Digital storytelling is one of learning model which is interesting and can be used to enhance EFL learners’ vocabulary. This study was aimed at describing the effectiveness of digital storytelling to enhance young learner vocabulary. The research used one group pretest-posttest design. There was two evaluation before and after the intervention to measure the effectiveness. The participant was twenty-nine students at state elementary school of Central Java, Indonesia. Quantitative data analysis i.e a score of vocabulary mastery was done by t-test. The research findings revealed that digital storytelling was effective to enhance EFL learner’s vocabulary, made them being joyful, relax, well-motivated, and having self-enthusiasm while learning English. Digital storytelling is a powerful learning activity based computer for EFL Learner’s to enhance their vocabulary.
{"title":"Digital Storytelling: Computer Based Learning Activity to Enhance Young Learner Vocabulary","authors":"Endang Sulistianingsih, Nur Aflahatun","doi":"10.2139/ssrn.3736914","DOIUrl":"https://doi.org/10.2139/ssrn.3736914","url":null,"abstract":"Vocabulary is very important in English language teaching but often ignored in learning activities. It is difficult for EFL learners to learn English with a lack of vocabulary. Digital storytelling is one of learning model which is interesting and can be used to enhance EFL learners’ vocabulary. This study was aimed at describing the effectiveness of digital storytelling to enhance young learner vocabulary. The research used one group pretest-posttest design. There was two evaluation before and after the intervention to measure the effectiveness. The participant was twenty-nine students at state elementary school of Central Java, Indonesia. Quantitative data analysis i.e a score of vocabulary mastery was done by t-test. The research findings revealed that digital storytelling was effective to enhance EFL learner’s vocabulary, made them being joyful, relax, well-motivated, and having self-enthusiasm while learning English. Digital storytelling is a powerful learning activity based computer for EFL Learner’s to enhance their vocabulary.","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130778122","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}
Walid Taleb, Théo Le Guenedal, Frédéric Lepetit, Vincent Mortier, Takaya Sekine, Lauren Stagnol
ESG investing's popularity has continually increased in the past five years. ESG data is increasingly integrated into investment processes. However, the information contained in ESG-related news for corporates has not been entirely exploited by institutional and long-only investors. The objective of this paper is to identify the benefits of ESG news information for active and factor-based investors. Indeed, one of the issues with ESG is the low frequency of score updates. For active management, we analyze ESG-sorted portfolios in investment universes filtered by ESG news volume. Metrics of ESG-related news are sourced from Truvalue Labs, a provider of Artificial Intelligence-powered ESG insights and analytics. We find that the approach of a universe focused on ESG news of corporates has been efficient in the early 2010s on the lower ESG-ranked side of the universe, but also on the higher ESG rank. More recently, it has positively contributed to more dynamic approaches of ESG investing. Finally, increasing the sensitivity to the highly visible SDGs significantly improves the return of ESG long-short portfolios.
{"title":"Corporate ESG News and The Stock Market","authors":"Walid Taleb, Théo Le Guenedal, Frédéric Lepetit, Vincent Mortier, Takaya Sekine, Lauren Stagnol","doi":"10.2139/ssrn.3723799","DOIUrl":"https://doi.org/10.2139/ssrn.3723799","url":null,"abstract":"ESG investing's popularity has continually increased in the past five years. ESG data is increasingly integrated into investment processes. However, the information contained in ESG-related news for corporates has not been entirely exploited by institutional and long-only investors. The objective of this paper is to identify the benefits of ESG news information for active and factor-based investors. Indeed, one of the issues with ESG is the low frequency of score updates. For active management, we analyze ESG-sorted portfolios in investment universes filtered by ESG news volume. Metrics of ESG-related news are sourced from Truvalue Labs, a provider of Artificial Intelligence-powered ESG insights and analytics. We find that the approach of a universe focused on ESG news of corporates has been efficient in the early 2010s on the lower ESG-ranked side of the universe, but also on the higher ESG rank. More recently, it has positively contributed to more dynamic approaches of ESG investing. Finally, increasing the sensitivity to the highly visible SDGs significantly improves the return of ESG long-short portfolios.","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123016976","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}
Deep neural networks have shown recent promise in many language-related tasks such as the modelling of conversations. We extend RNN-based sequence to sequence models to capture the long-range discourse across many turns of conversation. We perform a sensitivity analysis on how much additional context affects performance, and provide quantitative and qualitative evidence that these models can capture discourse relationships across multiple utterances. Our results show how adding an additional RNN layer for modelling discourse improves the quality of output utterances and providing more of the previous conversation as input also improves performance. By searching the generated outputs for specific discourse markers, we show how neural discourse models can exhibit increased coherence and cohesion in conversations.
{"title":"Neural Discourse Modelling of Conversations","authors":"John M. Pierre","doi":"10.2139/ssrn.3663042","DOIUrl":"https://doi.org/10.2139/ssrn.3663042","url":null,"abstract":"Deep neural networks have shown recent promise in many language-related tasks such as the modelling of conversations. We extend RNN-based sequence to sequence models to capture the long-range discourse across many turns of conversation. We perform a sensitivity analysis on how much additional context affects performance, and provide quantitative and qualitative evidence that these models can capture discourse relationships across multiple utterances. Our results show how adding an additional RNN layer for modelling discourse improves the quality of output utterances and providing more of the previous conversation as input also improves performance. By searching the generated outputs for specific discourse markers, we show how neural discourse models can exhibit increased coherence and cohesion in conversations.","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121184274","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}
In this paper, we develop FinBERT, a state-of-the-art deep learning algorithm that incorporates the contextual relations between words in the finance domain. First, using a researcher-labeled analyst report sample, we document that FinBERT significantly outperforms the Loughran and McDonald (LM) dictionary, the naïve Bayes, and Word2Vec in sentiment classification, primarily because of its ability to uncover sentiment in sentences that other algorithms mislabel as neutral. Next, we show that other approaches underestimate the textual informativeness of earnings conference calls by at least 32% compared with FinBERT. Our results also indicate that FinBERT’s greater accuracy is especially relevant when empirical tests may suffer from low power, such as with small samples. Last, textual sentiments summarized by FinBERT can better predict future earnings than the LM dictionary, especially after 2011, consistent with firms’ strategic disclosures reducing the information content of textual sentiments measured with LM dictionary. Our results have implications for academic researchers, investment professionals, and financial market regulators who want to extract insights from financial texts.
{"title":"FinBERT—A Deep Learning Approach to Extracting Textual Information","authors":"Allen Huang, Hui Wang, Yi Yang","doi":"10.2139/ssrn.3910214","DOIUrl":"https://doi.org/10.2139/ssrn.3910214","url":null,"abstract":"In this paper, we develop FinBERT, a state-of-the-art deep learning algorithm that incorporates the contextual relations between words in the finance domain. First, using a researcher-labeled analyst report sample, we document that FinBERT significantly outperforms the Loughran and McDonald (LM) dictionary, the naïve Bayes, and Word2Vec in sentiment classification, primarily because of its ability to uncover sentiment in sentences that other algorithms mislabel as neutral. Next, we show that other approaches underestimate the textual informativeness of earnings conference calls by at least 32% compared with FinBERT. Our results also indicate that FinBERT’s greater accuracy is especially relevant when empirical tests may suffer from low power, such as with small samples. Last, textual sentiments summarized by FinBERT can better predict future earnings than the LM dictionary, especially after 2011, consistent with firms’ strategic disclosures reducing the information content of textual sentiments measured with LM dictionary. Our results have implications for academic researchers, investment professionals, and financial market regulators who want to extract insights from financial texts.","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128229327","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}
Bag of words provides one way to deal with text representation and apply it to a standard type of text arrangement. This method depends on the idea of Bag-of-Words (BOW) that measures the content which is accessible from Wikipedia, Kaggle, Gmail and so on. The proposed method is utilized to create a Vector Space Model, which truly sustained into a Support Vector Machine classifier. This is to arrange and gathering of document records that are publically accessible datasets through social media. The text results demonstrate the examination between the raw information and the clean information that is viewed on the word cloud.
{"title":"Implementation on Text Classification Using Bag of Words Model","authors":"Nisha V M, D. Kumar R","doi":"10.2139/ssrn.3507923","DOIUrl":"https://doi.org/10.2139/ssrn.3507923","url":null,"abstract":"Bag of words provides one way to deal with text representation and apply it to a standard type of text arrangement. This method depends on the idea of Bag-of-Words (BOW) that measures the content which is accessible from Wikipedia, Kaggle, Gmail and so on. The proposed method is utilized to create a Vector Space Model, which truly sustained into a Support Vector Machine classifier. This is to arrange and gathering of document records that are publically accessible datasets through social media. The text results demonstrate the examination between the raw information and the clean information that is viewed on the word cloud.","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129613423","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}
This paper demonstrates that linguistic similarity predicts network tie formation and that friends exhibit linguistic convergence over time. Study 1 analyzes the linguistic styles and the emerging friendship network in a complete cohort of 285 students. Study 2 analyzes a large-scale dataset of online reviews. Across both studies, we collected data in two waves to examine changes in both friendship networks and linguistic styles. Using the LIWC linguistic framework, we analyze the text of students’ essays and of 1.7 million reviews by 159,651 Yelp reviewers. We find that similarity in linguistic style corresponds to higher likelihood of friendship formation and persistence, and that friendship ties, in turn, correspond with a convergence in linguistic style. We discuss the implications of the co-evolution of linguistic styles and social networks, which contribute to the formation of relational echo chambers.
{"title":"Language Style Similarity and Friendship Networks","authors":"Balázs Kovács, Adam M. Kleinbaum","doi":"10.2139/ssrn.3131715","DOIUrl":"https://doi.org/10.2139/ssrn.3131715","url":null,"abstract":"This paper demonstrates that linguistic similarity predicts network tie formation and that friends exhibit linguistic convergence over time. Study 1 analyzes the linguistic styles and the emerging friendship network in a complete cohort of 285 students. Study 2 analyzes a large-scale dataset of online reviews. Across both studies, we collected data in two waves to examine changes in both friendship networks and linguistic styles. Using the LIWC linguistic framework, we analyze the text of students’ essays and of 1.7 million reviews by 159,651 Yelp reviewers. We find that similarity in linguistic style corresponds to higher likelihood of friendship formation and persistence, and that friendship ties, in turn, correspond with a convergence in linguistic style. We discuss the implications of the co-evolution of linguistic styles and social networks, which contribute to the formation of relational echo chambers.","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122317000","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 : 2019-01-25DOI: 10.5121/ijnsa.2019.11103
A.F. Al Azzawi
Text documents are widely used, however, the text steganography is more difficult than other media because of a little redundant information. This paper presents a text steganography methodology appropriate for Arabic Unicode texts that do not use a normal sequential inserting process to overcome the security issues of the current approaches that are sensitive to steg-analysis. The Arabic Unicode text is kept within main unshaped letters, and the proposed method is used text file as cover text to hide a bit in each letter by reshaping the letters according to its position (beginning, middle, end of the word, or standalone), this hiding process is accomplished through multi-embedding layer where each layer contains all words with the same Tag detected using the POS tagger, and the embedding layers are selected randomly using the stego key to improve the security issues. The experimental result shows that the purposed method satisfied the hiding capacity requirements, improve security, and imperceptibility is better than currently developed approaches
{"title":"A Multi-Layer Arabic Text Steganographic Method Based on Letter Shaping","authors":"A.F. Al Azzawi","doi":"10.5121/ijnsa.2019.11103","DOIUrl":"https://doi.org/10.5121/ijnsa.2019.11103","url":null,"abstract":"Text documents are widely used, however, the text steganography is more difficult than other media because of a little redundant information. This paper presents a text steganography methodology appropriate for Arabic Unicode texts that do not use a normal sequential inserting process to overcome the security issues of the current approaches that are sensitive to steg-analysis. The Arabic Unicode text is kept within main unshaped letters, and the proposed method is used text file as cover text to hide a bit in each letter by reshaping the letters according to its position (beginning, middle, end of the word, or standalone), this hiding process is accomplished through multi-embedding layer where each layer contains all words with the same Tag detected using the POS tagger, and the embedding layers are selected randomly using the stego key to improve the security issues. The experimental result shows that the purposed method satisfied the hiding capacity requirements, improve security, and imperceptibility is better than currently developed approaches","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127392235","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}
This study deals with the politeness strategies of speakers of Russian, focusing on verbal expression of politeness. After running a field survey in schools in mid-2018, we try to analyze specific verbal markers of expressing politeness quantitatively. Four such markers were selected for this study, namely greeting, leave-taking, expressing gratitude and apology. Quantitative analysis shows that there is a clear frequency pattern found in these markers’ use, indicating a relatively high degree of sociolinguistic variation. Possible causes of this effect are discussed, including cultural diversity and multilingual setting of the modern Russian school communicative domain
{"title":"Politeness Strategies of Russian School Students: Quantitative Approach to Qualitative Data","authors":"M. Grabovskaya, E. Gridneva, A. Vlakhov","doi":"10.2139/ssrn.3296303","DOIUrl":"https://doi.org/10.2139/ssrn.3296303","url":null,"abstract":"This study deals with the politeness strategies of speakers of Russian, focusing on verbal expression of politeness. After running a field survey in schools in mid-2018, we try to analyze specific verbal markers of expressing politeness quantitatively. Four such markers were selected for this study, namely greeting, leave-taking, expressing gratitude and apology. Quantitative analysis shows that there is a clear frequency pattern found in these markers’ use, indicating a relatively high degree of sociolinguistic variation. Possible causes of this effect are discussed, including cultural diversity and multilingual setting of the modern Russian school communicative domain","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122104436","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}
Identifying the different varieties of the same language is more challenging than unrelated languages identification. In this paper, we propose an approach to discriminate language varieties or dialects of Mandarin Chinese for the Mainland China, Hong Kong, Taiwan, Macao, Malaysia and Singapore, a.k.a., the Greater China Region (GCR). When applied to the dialects identification of the GCR, we find that the commonly used character-level or word-level uni-gram feature is not very efficient since there exist several specific problems such as the ambiguity and context-dependent characteristic of words in the dialects of the GCR. To overcome these challenges, we use not only the general features like character-level n-gram, but also many new word-level features, including PMI-based and word alignment-based features. A series of evaluation results on both the news and open-domain dataset from Wikipedia show the effectiveness of the proposed approach.
{"title":"Sentence-Level Dialects Identification in the Greater China Region","authors":"Fan Xu, Mingwen Wang, Maoxi Li","doi":"10.5121/IJNLC.2016.5602","DOIUrl":"https://doi.org/10.5121/IJNLC.2016.5602","url":null,"abstract":"Identifying the different varieties of the same language is more challenging than unrelated languages identification. In this paper, we propose an approach to discriminate language varieties or dialects of Mandarin Chinese for the Mainland China, Hong Kong, Taiwan, Macao, Malaysia and Singapore, a.k.a., the Greater China Region (GCR). When applied to the dialects identification of the GCR, we find that the commonly used character-level or word-level uni-gram feature is not very efficient since there exist several specific problems such as the ambiguity and context-dependent characteristic of words in the dialects of the GCR. To overcome these challenges, we use not only the general features like character-level n-gram, but also many new word-level features, including PMI-based and word alignment-based features. A series of evaluation results on both the news and open-domain dataset from Wikipedia show the effectiveness of the proposed approach.","PeriodicalId":256367,"journal":{"name":"Computational Linguistics & Natural Language Processing eJournal","volume":"40 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123598389","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：