Named entity recognition(NER)in musk deer domain is the extraction of specific types of entities from unstructured texts,constituting a fundamental component of the knowledge graph,Q&A system,and text summarizatio...Named entity recognition(NER)in musk deer domain is the extraction of specific types of entities from unstructured texts,constituting a fundamental component of the knowledge graph,Q&A system,and text summarization system of musk deer domain.Due to limited annotated data,diverse entity types,and the ambiguity of Chinese word boundaries in musk deer domain NER,we present a novel NER model,CAELF-GP,which is based on cross-attention mechanism enhanced lexical features(CAELF).Specifically,we employ BERT as a character encoder and advocate the integration of external lexical information at the character representation layer.In the feature fusion module,instead of indiscriminately merging external dictionary information,we innovatively adopted a feature fusion method based on a cross-attention mechanism,which guides the model to focus on important lexical information by calculating the correlation between each character and its corresponding word sets.This module enhances the model’s semantic representation ability and entity boundary recognition capability.Ultimately,we introduce the decoding module of GlobalPointer(GP)for entity type recognition,capable of identifying both nested and non-nested entities.Since there is currently no publicly available dataset for the musk deer domain,we built a named entity recognition dataset for this domain by collecting relevant literature and working under the guidance of domain experts.The dataset facilitates the training and validation of the model and provides data foundation for subsequent related research.The model undergoes experimentation on two public datasets and the dataset of musk deer domain.The results show that it is superior to the baseline models,offering a promising technical avenue for the intelligent recognition of named entities in the musk deer domain.展开更多
Sentiment analysis is becoming increasingly important in today’s digital age, with social media being a significantsource of user-generated content. The development of sentiment lexicons that can support languages ot...Sentiment analysis is becoming increasingly important in today’s digital age, with social media being a significantsource of user-generated content. The development of sentiment lexicons that can support languages other thanEnglish is a challenging task, especially for analyzing sentiment analysis in social media reviews. Most existingsentiment analysis systems focus on English, leaving a significant research gap in other languages due to limitedresources and tools. This research aims to address this gap by building a sentiment lexicon for local languages,which is then used with a machine learning algorithm for efficient sentiment analysis. In the first step, a lexiconis developed that includes five languages: Urdu, Roman Urdu, Pashto, Roman Pashto, and English. The sentimentscores from SentiWordNet are associated with each word in the lexicon to produce an effective sentiment score. Inthe second step, a naive Bayesian algorithm is applied to the developed lexicon for efficient sentiment analysis ofRoman Pashto. Both the sentiment lexicon and sentiment analysis steps were evaluated using information retrievalmetrics, with an accuracy score of 0.89 for the sentiment lexicon and 0.83 for the sentiment analysis. The resultsshowcase the potential for improving software engineering tasks related to user feedback analysis and productdevelopment.展开更多
Social media is an essential component of our personal and professional lives. We use it extensively to share various things, including our opinions on daily topics and feelings about different subjects. This sharing ...Social media is an essential component of our personal and professional lives. We use it extensively to share various things, including our opinions on daily topics and feelings about different subjects. This sharing of posts provides insights into someone’s current emotions. In artificial intelligence (AI) and deep learning (DL), researchers emphasize opinion mining and analysis of sentiment, particularly on social media platforms such as Twitter (currently known as X), which has a global user base. This research work revolves explicitly around a comparison between two popular approaches: Lexicon-based and Deep learning-based Approaches. To conduct this study, this study has used a Twitter dataset called sentiment140, which contains over 1.5 million data points. The primary focus was the Long Short-Term Memory (LSTM) deep learning sequence model. In the beginning, we used particular techniques to preprocess the data. The dataset is divided into training and test data. We evaluated the performance of our model using the test data. Simultaneously, we have applied the lexicon-based approach to the same test data and recorded the outputs. Finally, we compared the two approaches by creating confusion matrices based on their respective outputs. This allows us to assess their precision, recall, and F1-Score, enabling us to determine which approach yields better accuracy. This research achieved 98% model accuracy for deep learning algorithms and 95% model accuracy for the lexicon-based approach.展开更多
Currently,the sentiment analysis research in the Malaysian context lacks in terms of the availability of the sentiment lexicon.Thus,this issue is addressed in this paper in order to enhance the accuracy of sentiment a...Currently,the sentiment analysis research in the Malaysian context lacks in terms of the availability of the sentiment lexicon.Thus,this issue is addressed in this paper in order to enhance the accuracy of sentiment analysis.In this study,a new lexicon for sentiment analysis is constructed.A detailed review of existing approaches has been conducted,and a new bilingual sentiment lexicon known as MELex(Malay-English Lexicon)has been generated.Constructing MELex involves three activities:seed words selection,polarity assignment,and synonym expansions.Our approach differs from previous works in that MELex can analyze text for the two most widely used languages in Malaysia,Malay,and English,with the accuracy achieved,is 90%.It is evaluated based on the experimentation and case study approaches where the affordable housing projects in Malaysia are selected as case projects.This finding has given an implication on the ability of MELex to analyze public sentiments in the Malaysian context.The novel aspects of this paper are two-fold.Firstly,it introduces the new technique in assigning the polarity score,and second,it improves the performance over the classification of mixed language content.展开更多
The mass data of social media and social networks generated by users play an important role in tracking users’sentiments and opinions online.A good polarity lexicon which can effectively improve the classification re...The mass data of social media and social networks generated by users play an important role in tracking users’sentiments and opinions online.A good polarity lexicon which can effectively improve the classification results of sentiment analysis is indispensable to analyze the user’s sentiments.Inspired by social cognitive theories,we combine basic emotion value lexicon and social evidence lexicon to improve traditional polarity lexicon.The proposed method obtains significant improvement in Chinese text sentiment analysis by using the proposed lexicon and new syntactic analysis method.展开更多
A novel method of constructing sentiment lexicon of new words(SLNW)is proposed to realize effective Weibo sentiment analysis by integrating existing lexicons of sentiments,lexicons of degree,negation and network.Based...A novel method of constructing sentiment lexicon of new words(SLNW)is proposed to realize effective Weibo sentiment analysis by integrating existing lexicons of sentiments,lexicons of degree,negation and network.Based on left-right entropy and mutual information(MI)neologism discovery algorithms,this new algorithm divides N-gram to obtain strings dynamically instead of relying on fixed sliding window when using Trie as data structure.The sentiment-oriented point mutual information(SO-PMI)algorithm with Laplacian smoothing is used to distinguish sentiment tendency of new words found in the data set to form SLNW by putting new words to basic sentiment lexicon.Experiments show that the sentiment analysis based on SLNW performs better than others.Precision,recall and F-measure are improved in both topic and non-topic Weibo data sets.展开更多
For a long time,there exists a considerable amount of sexism in English,especially in English lexicon.In this paper,the author will discuss some presentations of sexism in English lexicon,and try to analyze some facto...For a long time,there exists a considerable amount of sexism in English,especially in English lexicon.In this paper,the author will discuss some presentations of sexism in English lexicon,and try to analyze some factors which have a great influence on the existence of sexism in English.This paper wants to arouse more and more people to realize the importance and urgency of desexism.展开更多
Forensic linguistics, which is the interface between language and law, is a newly emerging interdiscipline in China. It belongs to neither the science of law nor the pure research category of linguistics, but it is an...Forensic linguistics, which is the interface between language and law, is a newly emerging interdiscipline in China. It belongs to neither the science of law nor the pure research category of linguistics, but it is an interdisciplinary subject based on these two disciplines. The linguistic issue in legal field is its key problem. At present, forensic linguistics in present China lays emphasis on written language instead of spoken language. This article gives a brief comparative analysis of Chinese and English forensic lexicon and the similarity of English and Chinese forensic lexicon. It also suggests that learners should view the differences between the two from the cultural perspective.展开更多
The focus of the thesis is the construction of multidimensional mental lexicon of second language. It is made up of four dimensions—dimension of meaning, dimension of pronunciation, dimension of orthography and dimen...The focus of the thesis is the construction of multidimensional mental lexicon of second language. It is made up of four dimensions—dimension of meaning, dimension of pronunciation, dimension of orthography and dimension of context so that through establishing these four dimensions, it comes into being.展开更多
The theories of mental lexicon explain how words are organized and accessed in human brain from the angle of psycho linguistics. It draws great interest to study on the field of psycholinguistics and SLA. This paper f...The theories of mental lexicon explain how words are organized and accessed in human brain from the angle of psycho linguistics. It draws great interest to study on the field of psycholinguistics and SLA. This paper focuses on incidental vocabulary acquisition of L2 and explores how to assist learners to reinforce and expand their network of mental lexicon by applying all kinds of mental connection in order to promote the learners to acquire English vocabulary.展开更多
Speaker variability is an important source of speech variations which makes continuous speech recognition a difficult task.Adapting automatic speech recognition(ASR) models to the speaker variations is a well-known st...Speaker variability is an important source of speech variations which makes continuous speech recognition a difficult task.Adapting automatic speech recognition(ASR) models to the speaker variations is a well-known strategy to cope with the challenge.Almost all such techniques focus on developing adaptation solutions within the acoustic models of the ASR systems.Although variations of the acoustic features constitute an important portion of the inter-speaker variations,they do not cover variations at the phonetic level.Phonetic variations are known to form an important part of variations which are influenced by both micro-segmental and suprasegmental factors.Inter-speaker phonetic variations are influenced by the structure and anatomy of a speaker's articulatory system and also his/her speaking style which is driven by many speaker background characteristics such as accent,gender,age,socioeconomic and educational class.The effect of inter-speaker variations in the feature space may cause explicit phone recognition errors.These errors can be compensated later by having appropriate pronunciation variants for the lexicon entries which consider likely phone misclassifications besides pronunciation.In this paper,we introduce speaker adaptive dynamic pronunciation models,which generate different lexicons for various speaker clusters and different ranges of speech rate.The models are hybrids of speaker adapted contextual rules and dynamic generalized decision trees,which take into account word phonological structures,rate of speech,unigram probabilities and stress to generate pronunciation variants of words.Employing the set of speaker adapted dynamic lexicons in a Farsi(Persian) continuous speech recognition task results in word error rate reductions of as much as 10.1% in a speaker-dependent scenario and 7.4% in a speaker-independent scenario.展开更多
The COVID-19 pandemic has spread globally,resulting in financialinstability in many countries and reductions in the per capita grossdomestic product.Sentiment analysis is a cost-effective method for acquiringsentiment...The COVID-19 pandemic has spread globally,resulting in financialinstability in many countries and reductions in the per capita grossdomestic product.Sentiment analysis is a cost-effective method for acquiringsentiments based on household income loss,as expressed on social media.However,limited research has been conducted in this domain using theLexDeep approach.This study aimed to explore social trend analytics usingLexDeep,which is a hybrid sentiment analysis technique,on Twitter to capturethe risk of household income loss during the COVID-19 pandemic.First,tweet data were collected using Twint with relevant keywords before(9 March2019 to 17 March 2020)and during(18 March 2020 to 21 August 2021)thepandemic.Subsequently,the tweets were annotated using VADER(lexiconbased)and fed into deep learning classifiers,and experiments were conductedusing several embeddings,namely simple embedding,Global Vectors,andWord2Vec,to classify the sentiments expressed in the tweets.The performanceof each LexDeep model was evaluated and compared with that of a supportvector machine(SVM).Finally,the unemployment rates before and duringCOVID-19 were analysed to gain insights into the differences in unemploymentpercentages through social media input and analysis.The resultsdemonstrated that all LexDeep models with simple embedding outperformedthe SVM.This confirmed the superiority of the proposed LexDeep modelover a classical machine learning classifier in performing sentiment analysistasks for domain-specific sentiments.In terms of the risk of income loss,the unemployment issue is highly politicised on both the regional and globalscales;thus,if a country cannot combat this issue,the global economy will alsobe affected.Future research should develop a utility maximisation algorithmfor household welfare evaluation,given the percentage risk of income lossowing to COVID-19.展开更多
Auditory discrimination is the ability to discriminate between words and sounds. Auditory discrimination can affect reading, spelling and writing. Several studies examined the correlation between auditory discriminati...Auditory discrimination is the ability to discriminate between words and sounds. Auditory discrimination can affect reading, spelling and writing. Several studies examined the correlation between auditory discrimination and reading performance. The aim of this study is to demonstrate the importance of auditory discrimination in the acquisition of mental lexicon and consequently the automation of reading in a sample of 101 students in their fourth year of primary education coming from four different schools in Kenitra (Morocco). The results analysis shows that reading scores correlated significantly with the auditory discrimination scores (r = 0.30, p 0.01). This proves that the inability to discriminate words causes a disability to store them in the mental lexicon, which makes it difficult to identify these words at a later encounter. This conclusion is supported by the significant correlation between reading and auditory and visual lexical decision tasks. In this study we were able to emphasize the importance of having good acoustic discrimination capacities for language development. Students who were successful at the auditory discrimination task are more successful at reading. A remediation program based on improving auditory discrimination capacities using the language assessment battery LABBEL could see reading performance improvement in these students.展开更多
This paper is based on two existing theories about automatic indexing of thematic knowledge concept. The prohibit-word table with position information has been designed. The improved Maximum Matching-Minimum Backtrack...This paper is based on two existing theories about automatic indexing of thematic knowledge concept. The prohibit-word table with position information has been designed. The improved Maximum Matching-Minimum Backtracking method has been researched. Moreover it has been studied on improved indexing algorithm and application technology based on rules and thematic concept word table.展开更多
Traumatic brain injury (TBI) can often influence the way subjects process and cope with their emotional life. In spite of the huge amount of studies investigating facial emotion recognition in subjects with traumatic ...Traumatic brain injury (TBI) can often influence the way subjects process and cope with their emotional life. In spite of the huge amount of studies investigating facial emotion recognition in subjects with traumatic brain injury, none of them has examined if their emotional lexicon, i.e. the ability to express emotions through words, may be affected. In this case-control study, we investigated the emotional lexicon of a group of 16 severe TBI subjects, comparing their performances with an healthy control group. A set of 25 visual stimuli (10 single picture images, 5 cartoon story pictures and 10 video clips) were selected. All the stimuli were chosen for their high emotional content by ten blind judges. The participants were asked to describe the stimuli, focusing on their emotional content. To get a better understanding of the correlates of emotional lexicon, all the participants were administered with the backward version of the Digit Span test, the Ekman and Friesen 60 Faces, the 20-Item Toronto Alexithymia Scale and the Empathy Quotient. Results pointed out a significant difference between TBI subjects and healthy controls only for cartoon story and video clip description. Conversely, TBI subjects performed similarly to controls when asked to describe the single picture images. A significant correlation was found in TBI subjects between the results of the Digit Span and number of emotional words, while no correlation was detected between emotional terms and the three scales used to assess TBI subjects’ emotional profile. These outcomes highlight that, for more complex stimuli, difficulties in emotional lexicon may depend on factors other than empathy, alexythimia or emotion recognition. These difficulties seem to be related to reduced working memory capacity, which prevent the subjects from correctly processing the emotional content of stimuli.展开更多
Translation lexicons are fundamental to natural language processing tasks like machine translation and cross language information retrieval. This paper presents a lexicon builder that can auto extract (or assist lexic...Translation lexicons are fundamental to natural language processing tasks like machine translation and cross language information retrieval. This paper presents a lexicon builder that can auto extract (or assist lexicographer in compiling) the word translations from Chinese English parallel corpus. Key mechanisms in this builder system are further described, including co occurrence measure, indirection association resolution and multi word unit translation. Experiment results indicate the effectiveness of the authors’ method and the potentiality of the lexicon builder system.展开更多
基金funded by 5·5 Engineering Research&Innovation Team Project of Beijing Forestry University(No.BLRC2023C02).
文摘Named entity recognition(NER)in musk deer domain is the extraction of specific types of entities from unstructured texts,constituting a fundamental component of the knowledge graph,Q&A system,and text summarization system of musk deer domain.Due to limited annotated data,diverse entity types,and the ambiguity of Chinese word boundaries in musk deer domain NER,we present a novel NER model,CAELF-GP,which is based on cross-attention mechanism enhanced lexical features(CAELF).Specifically,we employ BERT as a character encoder and advocate the integration of external lexical information at the character representation layer.In the feature fusion module,instead of indiscriminately merging external dictionary information,we innovatively adopted a feature fusion method based on a cross-attention mechanism,which guides the model to focus on important lexical information by calculating the correlation between each character and its corresponding word sets.This module enhances the model’s semantic representation ability and entity boundary recognition capability.Ultimately,we introduce the decoding module of GlobalPointer(GP)for entity type recognition,capable of identifying both nested and non-nested entities.Since there is currently no publicly available dataset for the musk deer domain,we built a named entity recognition dataset for this domain by collecting relevant literature and working under the guidance of domain experts.The dataset facilitates the training and validation of the model and provides data foundation for subsequent related research.The model undergoes experimentation on two public datasets and the dataset of musk deer domain.The results show that it is superior to the baseline models,offering a promising technical avenue for the intelligent recognition of named entities in the musk deer domain.
基金Researchers supporting Project Number(RSPD2024R576),King Saud University,Riyadh,Saudi Arabia.
文摘Sentiment analysis is becoming increasingly important in today’s digital age, with social media being a significantsource of user-generated content. The development of sentiment lexicons that can support languages other thanEnglish is a challenging task, especially for analyzing sentiment analysis in social media reviews. Most existingsentiment analysis systems focus on English, leaving a significant research gap in other languages due to limitedresources and tools. This research aims to address this gap by building a sentiment lexicon for local languages,which is then used with a machine learning algorithm for efficient sentiment analysis. In the first step, a lexiconis developed that includes five languages: Urdu, Roman Urdu, Pashto, Roman Pashto, and English. The sentimentscores from SentiWordNet are associated with each word in the lexicon to produce an effective sentiment score. Inthe second step, a naive Bayesian algorithm is applied to the developed lexicon for efficient sentiment analysis ofRoman Pashto. Both the sentiment lexicon and sentiment analysis steps were evaluated using information retrievalmetrics, with an accuracy score of 0.89 for the sentiment lexicon and 0.83 for the sentiment analysis. The resultsshowcase the potential for improving software engineering tasks related to user feedback analysis and productdevelopment.
文摘Social media is an essential component of our personal and professional lives. We use it extensively to share various things, including our opinions on daily topics and feelings about different subjects. This sharing of posts provides insights into someone’s current emotions. In artificial intelligence (AI) and deep learning (DL), researchers emphasize opinion mining and analysis of sentiment, particularly on social media platforms such as Twitter (currently known as X), which has a global user base. This research work revolves explicitly around a comparison between two popular approaches: Lexicon-based and Deep learning-based Approaches. To conduct this study, this study has used a Twitter dataset called sentiment140, which contains over 1.5 million data points. The primary focus was the Long Short-Term Memory (LSTM) deep learning sequence model. In the beginning, we used particular techniques to preprocess the data. The dataset is divided into training and test data. We evaluated the performance of our model using the test data. Simultaneously, we have applied the lexicon-based approach to the same test data and recorded the outputs. Finally, we compared the two approaches by creating confusion matrices based on their respective outputs. This allows us to assess their precision, recall, and F1-Score, enabling us to determine which approach yields better accuracy. This research achieved 98% model accuracy for deep learning algorithms and 95% model accuracy for the lexicon-based approach.
文摘Currently,the sentiment analysis research in the Malaysian context lacks in terms of the availability of the sentiment lexicon.Thus,this issue is addressed in this paper in order to enhance the accuracy of sentiment analysis.In this study,a new lexicon for sentiment analysis is constructed.A detailed review of existing approaches has been conducted,and a new bilingual sentiment lexicon known as MELex(Malay-English Lexicon)has been generated.Constructing MELex involves three activities:seed words selection,polarity assignment,and synonym expansions.Our approach differs from previous works in that MELex can analyze text for the two most widely used languages in Malaysia,Malay,and English,with the accuracy achieved,is 90%.It is evaluated based on the experimentation and case study approaches where the affordable housing projects in Malaysia are selected as case projects.This finding has given an implication on the ability of MELex to analyze public sentiments in the Malaysian context.The novel aspects of this paper are two-fold.Firstly,it introduces the new technique in assigning the polarity score,and second,it improves the performance over the classification of mixed language content.
基金the National Natural Science Foundation of China(No.61303094)the Doctoral Fund ofMinistry of Education of China(No.20123108120027)+2 种基金the Program of Science and Technology Commission of Shanghai Municipality(No.14511107100)the Shanghai Leading Academic Discipline Project(No.J50103)the Innovation Program of Shanghai Municipal Education Commission(No.14YZ024)
文摘The mass data of social media and social networks generated by users play an important role in tracking users’sentiments and opinions online.A good polarity lexicon which can effectively improve the classification results of sentiment analysis is indispensable to analyze the user’s sentiments.Inspired by social cognitive theories,we combine basic emotion value lexicon and social evidence lexicon to improve traditional polarity lexicon.The proposed method obtains significant improvement in Chinese text sentiment analysis by using the proposed lexicon and new syntactic analysis method.
基金Natural Science Foundation of Shanghai,China(No.18ZR1401200)Special Fund for Innovation and Development of Shanghai Industrial Internet,China(No.2019-GYHLW-01004)。
文摘A novel method of constructing sentiment lexicon of new words(SLNW)is proposed to realize effective Weibo sentiment analysis by integrating existing lexicons of sentiments,lexicons of degree,negation and network.Based on left-right entropy and mutual information(MI)neologism discovery algorithms,this new algorithm divides N-gram to obtain strings dynamically instead of relying on fixed sliding window when using Trie as data structure.The sentiment-oriented point mutual information(SO-PMI)algorithm with Laplacian smoothing is used to distinguish sentiment tendency of new words found in the data set to form SLNW by putting new words to basic sentiment lexicon.Experiments show that the sentiment analysis based on SLNW performs better than others.Precision,recall and F-measure are improved in both topic and non-topic Weibo data sets.
文摘For a long time,there exists a considerable amount of sexism in English,especially in English lexicon.In this paper,the author will discuss some presentations of sexism in English lexicon,and try to analyze some factors which have a great influence on the existence of sexism in English.This paper wants to arouse more and more people to realize the importance and urgency of desexism.
文摘Forensic linguistics, which is the interface between language and law, is a newly emerging interdiscipline in China. It belongs to neither the science of law nor the pure research category of linguistics, but it is an interdisciplinary subject based on these two disciplines. The linguistic issue in legal field is its key problem. At present, forensic linguistics in present China lays emphasis on written language instead of spoken language. This article gives a brief comparative analysis of Chinese and English forensic lexicon and the similarity of English and Chinese forensic lexicon. It also suggests that learners should view the differences between the two from the cultural perspective.
文摘The focus of the thesis is the construction of multidimensional mental lexicon of second language. It is made up of four dimensions—dimension of meaning, dimension of pronunciation, dimension of orthography and dimension of context so that through establishing these four dimensions, it comes into being.
文摘The theories of mental lexicon explain how words are organized and accessed in human brain from the angle of psycho linguistics. It draws great interest to study on the field of psycholinguistics and SLA. This paper focuses on incidental vocabulary acquisition of L2 and explores how to assist learners to reinforce and expand their network of mental lexicon by applying all kinds of mental connection in order to promote the learners to acquire English vocabulary.
文摘Speaker variability is an important source of speech variations which makes continuous speech recognition a difficult task.Adapting automatic speech recognition(ASR) models to the speaker variations is a well-known strategy to cope with the challenge.Almost all such techniques focus on developing adaptation solutions within the acoustic models of the ASR systems.Although variations of the acoustic features constitute an important portion of the inter-speaker variations,they do not cover variations at the phonetic level.Phonetic variations are known to form an important part of variations which are influenced by both micro-segmental and suprasegmental factors.Inter-speaker phonetic variations are influenced by the structure and anatomy of a speaker's articulatory system and also his/her speaking style which is driven by many speaker background characteristics such as accent,gender,age,socioeconomic and educational class.The effect of inter-speaker variations in the feature space may cause explicit phone recognition errors.These errors can be compensated later by having appropriate pronunciation variants for the lexicon entries which consider likely phone misclassifications besides pronunciation.In this paper,we introduce speaker adaptive dynamic pronunciation models,which generate different lexicons for various speaker clusters and different ranges of speech rate.The models are hybrids of speaker adapted contextual rules and dynamic generalized decision trees,which take into account word phonological structures,rate of speech,unigram probabilities and stress to generate pronunciation variants of words.Employing the set of speaker adapted dynamic lexicons in a Farsi(Persian) continuous speech recognition task results in word error rate reductions of as much as 10.1% in a speaker-dependent scenario and 7.4% in a speaker-independent scenario.
基金funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University,through the Research Groups Program Grant no.(RGP-1443-0045).
文摘The COVID-19 pandemic has spread globally,resulting in financialinstability in many countries and reductions in the per capita grossdomestic product.Sentiment analysis is a cost-effective method for acquiringsentiments based on household income loss,as expressed on social media.However,limited research has been conducted in this domain using theLexDeep approach.This study aimed to explore social trend analytics usingLexDeep,which is a hybrid sentiment analysis technique,on Twitter to capturethe risk of household income loss during the COVID-19 pandemic.First,tweet data were collected using Twint with relevant keywords before(9 March2019 to 17 March 2020)and during(18 March 2020 to 21 August 2021)thepandemic.Subsequently,the tweets were annotated using VADER(lexiconbased)and fed into deep learning classifiers,and experiments were conductedusing several embeddings,namely simple embedding,Global Vectors,andWord2Vec,to classify the sentiments expressed in the tweets.The performanceof each LexDeep model was evaluated and compared with that of a supportvector machine(SVM).Finally,the unemployment rates before and duringCOVID-19 were analysed to gain insights into the differences in unemploymentpercentages through social media input and analysis.The resultsdemonstrated that all LexDeep models with simple embedding outperformedthe SVM.This confirmed the superiority of the proposed LexDeep modelover a classical machine learning classifier in performing sentiment analysistasks for domain-specific sentiments.In terms of the risk of income loss,the unemployment issue is highly politicised on both the regional and globalscales;thus,if a country cannot combat this issue,the global economy will alsobe affected.Future research should develop a utility maximisation algorithmfor household welfare evaluation,given the percentage risk of income lossowing to COVID-19.
文摘Auditory discrimination is the ability to discriminate between words and sounds. Auditory discrimination can affect reading, spelling and writing. Several studies examined the correlation between auditory discrimination and reading performance. The aim of this study is to demonstrate the importance of auditory discrimination in the acquisition of mental lexicon and consequently the automation of reading in a sample of 101 students in their fourth year of primary education coming from four different schools in Kenitra (Morocco). The results analysis shows that reading scores correlated significantly with the auditory discrimination scores (r = 0.30, p 0.01). This proves that the inability to discriminate words causes a disability to store them in the mental lexicon, which makes it difficult to identify these words at a later encounter. This conclusion is supported by the significant correlation between reading and auditory and visual lexical decision tasks. In this study we were able to emphasize the importance of having good acoustic discrimination capacities for language development. Students who were successful at the auditory discrimination task are more successful at reading. A remediation program based on improving auditory discrimination capacities using the language assessment battery LABBEL could see reading performance improvement in these students.
基金the Science Foundation of Shanghai Archive Bureau (0215)
文摘This paper is based on two existing theories about automatic indexing of thematic knowledge concept. The prohibit-word table with position information has been designed. The improved Maximum Matching-Minimum Backtracking method has been researched. Moreover it has been studied on improved indexing algorithm and application technology based on rules and thematic concept word table.
文摘Traumatic brain injury (TBI) can often influence the way subjects process and cope with their emotional life. In spite of the huge amount of studies investigating facial emotion recognition in subjects with traumatic brain injury, none of them has examined if their emotional lexicon, i.e. the ability to express emotions through words, may be affected. In this case-control study, we investigated the emotional lexicon of a group of 16 severe TBI subjects, comparing their performances with an healthy control group. A set of 25 visual stimuli (10 single picture images, 5 cartoon story pictures and 10 video clips) were selected. All the stimuli were chosen for their high emotional content by ten blind judges. The participants were asked to describe the stimuli, focusing on their emotional content. To get a better understanding of the correlates of emotional lexicon, all the participants were administered with the backward version of the Digit Span test, the Ekman and Friesen 60 Faces, the 20-Item Toronto Alexithymia Scale and the Empathy Quotient. Results pointed out a significant difference between TBI subjects and healthy controls only for cartoon story and video clip description. Conversely, TBI subjects performed similarly to controls when asked to describe the single picture images. A significant correlation was found in TBI subjects between the results of the Digit Span and number of emotional words, while no correlation was detected between emotional terms and the three scales used to assess TBI subjects’ emotional profile. These outcomes highlight that, for more complex stimuli, difficulties in emotional lexicon may depend on factors other than empathy, alexythimia or emotion recognition. These difficulties seem to be related to reduced working memory capacity, which prevent the subjects from correctly processing the emotional content of stimuli.
文摘Translation lexicons are fundamental to natural language processing tasks like machine translation and cross language information retrieval. This paper presents a lexicon builder that can auto extract (or assist lexicographer in compiling) the word translations from Chinese English parallel corpus. Key mechanisms in this builder system are further described, including co occurrence measure, indirection association resolution and multi word unit translation. Experiment results indicate the effectiveness of the authors’ method and the potentiality of the lexicon builder system.
