Speech Classification Research Articles

SPEECH ACT ANALYSIS REFLECTED ON FEMALE DIGITAL COMIC MAKERS OF UIN RADEN MAS SAID SURAKARTA

This study discusses speech acts in the Digital Comics discourse made by UIN Raden Mas Said Surakarta students who are members of the Creative Digital Skills Development Class. The comic discourse campaigns for the importance of tolerance from both religion and fellow human beings. The digital comics were created in a creative digital skills class held by the English Literature study program at UIN Raden Mas Said Surakarta. Through digital comic discourse, female students create their ideas with the theme of tolerance. By using Searle’s theory, speech act analysis in the discourse is carried out. Searle gave further categories of illocutionary speech acts into representative, directive, commissive, expressive, and declarative categories. These categories make it easier for researchers to see specifically the intended meaning. The data from this study emphasize the utterances spoken by the main characters of the comics. In addition, images from the data become secondary data from this study because the discourse consists of two units, namely text (verbal) and images (non-verbal). The data is processed and classified into several speech act classifications proposed by Searle. The data is described by the qualitative method. The results of this study indicate that speech acts reflected from digital comics by students of UIN Raden Mas Said Surakarta have topics that refer to tolerance and maintaining harmony between religions or friends. In this work, students took three main sub-themes, namely 1) inter-religious harmony, 2) harmony among friends, and 3) harmony among neighbors. Character emphasizes the female character. The stories of the characters also affect the storyline, most of which emphasize caring and caring for each other, especially for women of different religions or different backgrounds. In terms of speech acts, from the 15 data collected, there are Directive, Expressive, and Representative with the directive portion being more dominant. The results show that 46.2 percent of the main characters show directive speech acts. Expressive speech acts show the second dominant speech act with a percentage of 33 percent. While the representative 13.2 percent in representative speech acts. While the declarative percentage shows 6.6 percent. From this percentage, it can be concluded that the use of directive speech acts is the main and most effective reference in conveying the moral message of an invitation, namely an invitation to maintain harmony. While expressive speech acts are used as speech acts that reflect empathy for others. In this case empathy between friends or religion.

Norms of Constatives

AbstractAccording to the normative approach, speech acts are governed by certain norms. Interestingly, the same is true for classes of speech acts. This paper considers the normative treatment of constatives, consisting of such classes as assertives, predictives, suggestives, and more. The classical approach is to treat these classes of illocutions as species of constatives. Recently, however, Simion (Shifty Speech and Independent Thought: Epistemic Normativity in Context, Oxford University Press, 2021) has proposed that all constatives (i) are species of assertion, and (ii) are governed by the knowledge norm. I defend the classical treatment of constatives and show that Simion’s conclusion is untenable. No taxonomy of speech acts can accommodate such a view. More importantly, we can test whether a particular speech act is an assertion or not. I propose five tests of assertion, the passing of which is a necessary condition for being an assertion. Some constative speech acts fail these tests. Thus, contrary to Simion, not all constatives can be regarded as species of assertion.

Phonetic category activation predicts the direction and magnitude of perceptual adaptation to accented speech.

Unfamiliar accents can systematically shift speech acoustics away from community norms and reduce comprehension. Yet, limited exposure improves comprehension. This perceptual adaptation indicates that the mapping from acoustics to speech representations is dynamic, rather than fixed. But, what drives adjustments is debated. Supervised learning accounts posit that activation of an internal speech representation via disambiguating information generates predictions about patterns of speech input typically associated with the representation. When actual input mismatches predictions, the mapping is adjusted. We tested two hypotheses of this account across consonants and vowels as listeners categorized speech conveying an English-like acoustic regularity or an artificial accent. Across conditions, signal manipulations impacted which of two acoustic dimensions best conveyed category identity, and predicted which dimension would exhibit the effects of perceptual adaptation. Moreover, the strength of phonetic category activation, as estimated by categorization responses reliant on the dominant acoustic dimension, predicted the magnitude of adaptation observed across listeners. The results align with predictions of supervised learning accounts, suggesting that perceptual adaptation arises from speech category activation, corresponding predictions about the patterns of acoustic input that align with the category, and adjustments in subsequent speech perception when input mismatches these expectations. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

한국 텔레비전 대담방송 영상에 있어서의 발화자 등장 비율 －표정을 기준으로－

This study aimed to measure the rate of speaker appearances by examining video footage of individualized interviews from the television program, Tales of Modern Korean History: TV Autobiographies. The appearance rate was calculated based on the possibility of observing the speaker’s facial expressions. Speakers appeared in approximately 80 per cent of all conversations, however, the ratio varied according to the role of the speaker and type of speech. The conversations were classified into three speech categories: expressing agreement, questioning, and expressing neutral opinions. The rate of expression of agreement was the lowest compared to the other categories while the rate for questioning was similar to that of expression of neutral opinions. Moreover, the rate of speaker appearance for all categories was higher for the interviewee than the interviewer. The proportion of a person’s appearance within the video footage also differs for the interviewer and interviewee, with a full body shot of the speaker often used at the beginning of the questioning process. Additional studies need to be conducted on other television programs, to confirm the generalization of this trend specific to Korean interview-based television programs.

Face Threatening Acts in Political Discourse: A Case of the Building Bridges Initiative in Kenya

Cut-throat competitions have, in recent times, characterised Kenyan politics. Political contestants use language in these competitions. How well these politicians package and sell their agenda depends on their choice of words and complementary paralinguistic features. Political contenders fend off opposition through utterances hence making politics largely a game of words. In a multiparty and multi-ethnic state like Kenya, every political party and ethnic group always have differing interests at a given time, often sparking bitter exchanges between politicians from different camps. Individuals, activists, activist groups, and commissions have often accused the political class of hate speech and insensitive language. This study, alive to the aforementioned, is an attempt at a pragmatic examination of the verbal communication of the Kenyan political class as they differ in ideas over a highly contested matter of national political interest, in this case, the Building Bridges Initiative (henceforth BBI). The study benefits from Brown's and Levinson's (1987) Politeness. Austin's (1962) Speech Acts Theory complements politeness theory. The study adopts an analytical research design of the discourse of five politicians purposively sampled from two events where the matters of BBI issues were the main agenda of discussion. Face Threatening Acts (FTAs) were elicited and explained analytically from the speaker's talks. A descriptive qualitative research technique is used in the analysis of data. The study finds that the political class in Kenya employs both positive and negative FTAs proposed by Brown and Levinson (1987) to achieve means to their ends. This study concludes that several FTAs are employed in political discourse in Kenya, and these FTAs reinforce the effectiveness of communication on such platforms.

Hate Speech Hashtag Classification on Twitter Using the Hybrid Classifier Method

Hate speech on social media, especially Twitter, often takes the form of racism, sexism, or political interests aimed at certain individuals or groups. These actions can trigger crime, riots, violence and even resistance to individuals or groups. Therefore, we need a process of classifying a tweet whether it is hate speech or not to reduce the abuse that occurs on Twitter. The technology used in the classification of hate speech that is most commonly used is neural networks that require user data and meta data. In previous studies, the Naïve Bayes (NB) method has been used using the bigram, unigram and feature selection features with an accuracy of 80-85%. The k-Nearest Neighbor (kNN) method has also been used which has an accuracy of 70-85% on the clarification of hate speech by political figures. Meanwhile, the most widely used method is the Support Vector Machine (SVM) method with an accuracy of 70 to the highest 95%. To get a higher accuracy in the classification of hate speech, this study will perform a Hybrid Classifier on the Hate Speech Hashtag Classification process using a combination method of MLP, kNN, NB. The data used in this study are Twitter Tweets from November 2021 to June 2022 regarding trending hashtags. The average accuracy performance results obtained using MLP, kNN, NB were 72%, 63%,73% respectively. To improve the accuracy of the classification results of the three methods, a combination of methods using the Hybrid Classifier is carried out. Experimental results show Hybrid Classifier with voting method can increase accuracy up to 74%. It was found that the use of a hybrid can provide a better system performance than the 3 classifiers in its composition, namely kNN, NB and MLP

Implementation of BERT, IndoBERT, and CNN-LSTM in Classifying Public Opinion about COVID-19 Vaccine in Indonesia

COVID-19 was classified as a pandemic in March 2020, and then in July 2021, this virus had its variance that spreads all over the world including Indonesia. The probability of the detrimental of its effect cannot be avoided, because this virus has a huge transmission risk during daily activity. To prevent suffering from COVID-19, people certainly need to be vaccinated. In responding to its vaccine, the citizen of Indonesia become expressive, so they try to express opinions, for example by uploading text on Twitter. Those expressions can be learned using deep learning frameworks which are BERT, CNN-LSTM, and IndoBERTweet to get knowledge about negative speech categories such as anxiety, panic, and emotion, or positive speech such as vaccines whether worked well. By then, these three methods accomplish in carrying out the prediction of sentiments about vaccination using dataset tweets on Twitter from January-2021 to March-2022, for instance using IndoBERT succeeds to classify sentiments as positive sentiment at around 80%, and then IndoBERTweet at 68%, in addition using CNN-LSTM reach 53% with the total of using 2020 dataset from Twitter. According to these results, a lesson learned for continued improvement for Indonesia's Government or authorities can be acquired in ending the COVID-19 pandemic.

AN ANALYSIS OF SPEECH ACT DURING SPEAKING CLASS ACTIVITY (TEACHER – STUDENTS TALKS)

This research focuses on speech acts as a significant role in teaching and learning process. In line with this topic, the aimed of this research attempts to find out the types of speech act mostly used by teachers’ and students’ English program. This study used descriptive qualitative method. The data which were used the utterances performed by the teacher and students talk in speaking class. Those speech acts are supported by theories of Searle (1977) who find out the use of speech act. From the theory, there are 5 classifications of illocutionary speech act; representative, directive, expressive, commissive, and declarative. The findings show that the classifications of speech acts mostly used by teacher is directive and representative is mostly used by the students. From the findings, teacher’s directive has some involvement toward students’ behavior during teaching and learning process. Besides, the used of representative by students has enhances their speaking ability. This study concludes that when teacher and students used the speech acts, it helps them comprehend the message in every utterance and easy to understand when communication. Hopefully, this study will help develop good classroom communication between teachers and students.

한국 단편소설의 화법과 영어번역에 관한 논의 - 오정희의 ｢동경｣을 기반으로 -

In fictional narrative, the character’s speech and thought is presented in meaningful and sometimes complex ways. It has been shown that choosing modes of speech and thought presentation is an important aspect of writing that could affect the reading experience. Nevertheless, there is little research on how modes of speech and thought can be (re)constructed for a different readership. This study analyzes the modes of speech and thought presentation in The Bronze Mirror ― Bruce and Ju-Chan Fulton’s translation of O Chŏnghŭi’s “Tonggyŏng.” The original and translated texts are compared in detail, according to Leech and Short’s (2007) categories of speech and thought presentation, i.e., direct speech/thought, free direct speech/thought, indirect speech/thought, free indirect speech/thought, and narrative report of a speech/thought act. Findings show that in general the translators used complex modes of presentation encoded in the original. However, in some narrative situations, they used different modes of presentation to make the unfolding narrative accessible and cohesive. This article concludes with a brief discussion of how to better translate fiction in terms of speech and thought presentation.

Enhanced Seagull Optimization with Natural Language Processing Based Hate Speech Detection and Classification

Hate speech has become a hot research topic in the area of natural language processing (NLP) due to the tremendous increase in the usage of social media platforms like Instagram, Twitter, Facebook, etc. The facelessness and flexibility provided through the Internet have made it easier for people to interact aggressively. Furthermore, the massive quantity of increasing hate speech on social media with heterogeneous sources makes it a challenging task. With this motivation, this study presents an Enhanced Seagull Optimization with Natural Language Processing Based Hate Speech Detection and Classification (ESGONLP-HSC) model. The major intention of the presented ESGONLP-HSC model is to identify and classify the occurrence of hate speech on social media websites. To accomplish this, the presented ESGONLP-HSC model involves data pre-processing at several stages, such as tokenization, vectorization, etc. Additionally, the Glove technique is applied for the feature extraction process. In addition, an attention-based bidirectional long short-term memory (ABLSTM) model is utilized for the classification of social media text into three classes such as neutral, offensive, and hate language. Moreover, the ESGO algorithm is utilized as a hyperparameter optimizer to adjust the hyperparameters related to the ABLSTM model, which shows the novelty of the work. The experimental validation of the ESGONLP-HSC model is carried out, and the results are examined under diverse aspects. The experimentation outcomes reported the promising performance of the ESGONLP-HSC model over recent state of art approaches.

The acquisition of speech categories: beyond perceptual narrowing, beyond unsupervised learning and beyond infancy

ABSTRACT An early achievement in language is carving a variable acoustic space into categories. The canonical story is that infants accomplish this by the second year, when only unsupervised learning is plausible. I challenge this view, synthesising five lines of developmental, phonetic and computational work. First, unsupervised learning may be insufficient given the statistics of speech (including infant-directed). Second, evidence that infants “have” speech categories rests on tenuous methodological assumptions. Third, the fact that the ecology of the learning environment is unsupervised does not rule out more powerful error driven learning mechanisms. Fourth, several implicit supervisory signals are available to older infants. Finally, development is protracted through adolescence, enabling richer avenues for development. Infancy may be a time of organising the auditory space, but true categorisation only arises via complex developmental cascades later in life. This has implications for critical periods, second language acquisition, and our basic framing of speech perception.

Development of categorical speech perception in Mandarin-speaking children and adolescents.

Although children develop categorical speech perception at a very young age, the maturation process remains unclear. A cross-sectional study in Mandarin-speaking 4-, 6-, and 10-year-old children, 14-year-old adolescents, and adults (n=104, 56 males, all Asians from mainland China) was conducted to investigate the development of categorical perception of four Mandarin phonemic contrasts: lexical tone contrast Tone 1-2, vowel contrast /u/-/i/, consonant aspiration contrast /p/-/ph /, and consonant formant transition contrast /p/-/t/. The results indicated that different types of phonemic contrasts, and even the identification and discrimination of the same phonemic contrast, matured asynchronously. The observation that tone and vowel perception are achieved earlier than consonant perception supports the phonological saliency hypothesis.

Methodology of analysis of directive speech acts in English and Arabic academic discourse

This article presents the author's methodology for analyzing directive speech acts in English and Arabic academic discourse, developed during the writing of the author's dissertation research. The purpose of the article is to describe and confirm the effectiveness of the methodology for analyzing directive speech acts within the framework of two academic discourses. In addition to substantiating the choice of research methods and respondent groups, the article presents a written discursive test with situational examples developed on the basis of the classification of directive speech acts by J. Serle (1979). We propose the study of directive speech acts from the point of view of grammatical, cultural, social and lexical aspects. The purpose of this article is an attempt to propose the author's methodology for analyzing directive speech acts in a comparative aspect within the framework of academic discourse functioning in English and Arabic. The novelty of the research lies in the fact that earlier in Russian and foreign linguistics, no attempts were made to develop a methodology for analyzing directive speech acts in a comparative perspective of English and Arabic. In conclusion, the author makes a conclusion about the effectiveness of the proposed method of analysis, and also notes the prospects for further research on the proposed topic. The results of the article can be used in the compilation of methodological complexes for teaching comparative linguistics, as well as courses on discourse analysis in higher educational institutions.

Survey of Graph Neural Networks and Applications

The advance of deep learning has shown great potential in applications (speech, image, and video classification). In these applications, deep learning models are trained by datasets in Euclidean space with fixed dimensions and sequences. Nonetheless, the rapidly increasing demands on analyzing datasets in non-Euclidean space require additional research. Generally speaking, finding the relationships of elements in datasets and representing such relationships as weighted graphs consisting of vertices and edges is a viable way of analyzing datasets in non-Euclidean space. However, analyzing the weighted graph-based dataset is a challenging problem in existing deep learning models. To address this issue, graph neural networks (GNNs) leverage spectral and spatial strategies to extend and implement convolution operations in non-Euclidean space. Based on graph theory, a number of enhanced GNNs are proposed to deal with non-Euclidean datasets. In this study, we first review the artificial neural networks and GNNs. We then present ways to extend deep learning models to deal with datasets in non-Euclidean space and introduce the GNN-based approaches based on spectral and spatial strategies. Furthermore, we discuss some typical Internet of Things (IoT) applications that employ spectral and spatial convolution strategies, followed by the limitations of GNNs in the current stage.

Classification of Silent Speech in English and Bengali Languages Using Stacked Autoencoder

Classification of Silent Speech in English and Bengali Languages Using Stacked Autoencoder

Multiclass Classification of Imagined Speech Vowels and Words of Electroencephalography Signals Using Deep Learning

The paper’s emphasis is on the imagined speech decoding of electroencephalography (EEG) neural signals of individuals in accordance with the expansion of the brain-computer interface to encompass individuals with speech problems encountering communication challenges. Decoding an individual’s imagined speech from nonstationary and nonlinear EEG neural signals is a complex task. Related research work in the field of imagined speech has revealed that imagined speech decoding performance and accuracy require attention to further improve. The evolution of deep learning technology increases the likelihood of decoding imagined speech from EEG signals with enhanced performance. We proposed a novel supervised deep learning model that combined the temporal convolutional networks and the convolutional neural networks with the intent of retrieving information from the EEG signals. The experiment was carried out using an open-access dataset of fifteen subjects’ imagined speech multichannel signals of vowels and words. The raw multichannel EEG signals of multiple subjects were processed using discrete wavelet transformation technique. The model was trained and evaluated using the preprocessed signals, and the model hyperparameters were adjusted to achieve higher accuracy in the classification of imagined speech. The experiment results demonstrated that the multiclass imagined speech classification of the proposed model exhibited a higher overall accuracy of 0.9649 and a classification error rate of 0.0350. The results of the study indicate that individuals with speech difficulties might well be able to leverage a noninvasive EEG-based imagined speech brain-computer interface system as one of the long-term alternative artificial verbal communication mediums.

AN ANALYSIS OF SPEECH ACT DURING SPEAKING CLASS ACTIVITY (TEACHER – STUDENTS TALKS)

Abstract.This research focuses on speech acts as a significant role in teaching and learning process. In line with this topic, the aim of this research is to find out the types of speech act mostly used by teachers’ and students’ English program. This study used descriptive qualitative method. The data used were the utterances performed by the teacher and students talk in speaking class. Those speech acts are supported by theories of Searle & Suherdi (1976), who find out the use of speech act. From the theory, there are 5 classifications of illocutionary speech act; representative,directive, expressive, commissive, and declarative. The findings show that the classifications of speech acts mostly used by teacher is directive while representative is mostly used by the students. From the findings, teacher’s directive has some involvement toward students’ behavior during teaching and learning process. Besides, the use of representative by students has enhanced their speaking ability. This study concludes that when teacher and students used the speech acts, it helpsthem comprehend the message in every utterance and easy to understand when communication. Hopefully, this study will help develop good classroom communication between teachers and students.

When AI moderates online content: effects of human collaboration and interactive transparency on user trust

Abstract Given the scale of user-generated content online, the use of artificial intelligence (AI) to flag problematic posts is inevitable, but users do not trust such automated moderation of content. We explore if (a) involving human moderators in the curation process and (b) affording “interactive transparency,” wherein users participate in curation, can promote appropriate reliance on AI. We test this through a 3 (Source: AI, Human, Both) × 3 (Transparency: No Transparency, Transparency-Only, Interactive Transparency) × 2 (Classification Decision: Flagged, Not Flagged) between-subjects online experiment (N = 676) involving classification of hate speech and suicidal ideation. We discovered that users trust AI for the moderation of content just as much as humans, but it depends on the heuristic that is triggered when they are told AI is the source of moderation. We also found that allowing users to provide feedback to the algorithm enhances trust by increasing user agency.

COMMUNICATIVE-PRAGMATIC FEATURES OF THE GOSSIP GENRE

The purpose of the article is to establish the illocutionary aims of praise and compliment speech acts. The object of the study is praise and compliment speech acts, depicted in the English-language communication of the personages of fictional discourse. The scope of study is the general and differential illocutionary aims of praise and compliment speech acts in the personages’ communication of fictional discourse. The work is based on the method of observation and contextual-interpretive analysis. The result of the study of the problem was the definition of praise and compliment as related positively evaluative speech acts that combine the features of expressives, behabitives, satisfactives and sometimes function as phatic speech acts. Both acts are aimed at expressing positive evaluation, positive impact on the recipient's emotions, creating a favourable atmosphere for communication and observing a social ritual. Conclusions: a part from the general illocutionary aims of praise and compliment speech acts, differential illocutionary aims have been established and analyzed in the personages’ communication of modern fictional English-language discourse. The practical value of the investigation is seen in the offered classification of speech act illocutionary aims that can serve as a possible model for research of speech acts.

Trump’s hateful rhetoric and First Amendment failures: Re-envisioning incitement, true threats, and hate speech

ABSTRACT Donald Trump’s hate-filled rhetoric while in office emphasizes long-existing shortcomings of free speech doctrine dealing with various forms of threatening speech. More so, because of his elected position during those speech moments, his speech elevates those concerns to a new level. His disregard for civil discourse has opened the door for a new speech behavior in national politics, one where inciteful, threatening or hateful speech is used more frequently and, as such, is becoming more socially acceptable. Each of those speech moments invokes claims of First Amendment protection. All of them were unimaginable topics 50 years ago and yet, from a legal perspective, all were or would be judged today using principles and legal doctrines crystalized in the 1950s and 1960s. Clearly, these are different times but what, if anything, does that mean for claims to free speech protections? This paper maintains that the answer to the problems inherent in current First Amendment treatment of hate-filled political speech involves two actions. First, the pre-existing doctrines of incitement and true threats need to be updated to make them applicable to current communication formats. Second, the courts must consider the addition of a constitutional category of hate speech.