TRG-DAtt: The Target Relational Graph and Double Attention Network Based Sentiment Analysis and Prediction for Supporting Decision Making

The management of public opinion and the use of big data monitoring to accurately judge and verify all kinds of information are valuable aspects in the enterprise management decision-making process. The sentiment analysis of reviews is a key decision-making tool for e-commerce development. Most existing review sentiment analysis methods involve sequential modeling but do not focus on the semantic relationships. However, Chinese semantics are different from English semantics in terms of the sentence structure. Irrelevant contextual words may be incorrectly identified as cues for sentiment prediction. The influence of the target words in reviews must be considered. Thus, this paper proposes the TRG-DAtt model for sentiment analysis based on target relational graph (TRG) and double attention network (DAtt) to analyze the emotional information to support decision making. First, dependency tree-based TRG is introduced to independently and fully mine the semantic relationships. We redefine and constrain the dependency and use it as the edges to connect the target and context words. Second, we design dependency graph attention network (DGAT) and interactive attention network (IAT) to form the DAtt and obtain the emotional features of the target words and reviews. DGAT models the dependency of the TRG by aggregating the semantic information. Next, the target emotional enhancement features obtained by the DGAT are input to the IAT. The influence of each target word on the review can be obtained through the interaction. Finally, the target emotional enhancement features are weighted by the impact factor to generate the review's emotional features. In this study, extensive experiments were conducted on the car and Meituan review data sets, which contain consumer reviews on cars and stores, respectively. The results demonstrate that the proposed model outperforms the existing models.

Transparent Aspect-Level Sentiment Analysis Based on Dependency Syntax Analysis and Its Application on COVID-19

Aspect-level sentiment analysis identifies fine-grained emotion for target words. There are three major issues in current models of aspect-level sentiment analysis. First, few models consider the natural language semantic characteristics of the texts. Second, many models consider the location characteristics of the target words, but ignore the relationships among the target words and among the overall sentences. Third, many models lack transparency in data collection, data processing, and results generating in sentiment analysis. In order to resolve these issues, we propose an aspect-level sentiment analysis model that combines a bidirectional Long Short-Term Memory (LSTM) network and a Graph Convolutional Network (GCN) based on Dependency syntax analysis (Bi-LSTM-DGCN). Our model integrates the dependency syntax analysis of the texts, and explicitly considers the natural language semantic characteristics of the texts. It further fuses the target words and overall sentences. Extensive experiments are conducted on four benchmark datasets, i.e., Restaurant14, Laptop, Restaurant16, and Twitter. The experimental results demonstrate that our model outperforms other models like Target-Dependent LSTM (TD-LSTM), Attention-based LSTM with Aspect Embedding (ATAE-LSTM), LSTM+SynATT+TarRep and Convolution over a Dependency Tree (CDT). Our model is further applied to aspect-level sentiment analysis on “government” and “lockdown” of 1,658,250 tweets about “#COVID-19” that we collected from March 1, 2020 to July 1, 2020. The experimental results show that Twitter users’ positive and negative sentiments fluctuated over time. Through the transparency analysis in data collection, data processing, and results generating, we discuss the reasons for the evolution of users’ emotions over time based on the tweets and on our models.

Successful Translation Students’ Use of Dictionaries

Dictionaries of all types are an indispensable tool for both professional and trainee translators. However, the literature on trainee translators indicates that the skills associated with dictionary use have not been given the required attention. Knowing which dictionaries to use and how to use them efficiently when engaged in the translation process are significant aspects of translation pedagogy. In fact, facilitating the development of effective dictionary use helps develop translation competence in general. Therefore, the present article reports on a qualitative case study of successful translation students’ usage of and preferences for various types of dictionaries. The results show that successful trainee translators use dictionaries to locate synonyms or better translations for target words. Successful translation students are also reported to use dictionaries frequently to check spelling. Most respondents reported consulting the dictionary after they finished reading source texts. In line with the global move toward digitalization, the participants reported using electronic dictionaries with significantly greater frequency than paper dictionaries. In most cases, successful translation students’ use of paper dictionaries was limited to classroom examinations. The open-ended interview questions also helped to reveal the variety of dictionaries used by this group of trainee translators. Taken together, these findings have utility for translation instructors, particularly regarding the improvement of trainee translators’ experiences and the provision of assistance to less successful students.

Increased cognitive load during pseudoword processing

Pseudowords (words without semantic meaning) are often used as a control condition in linguistic cognitive experiments, with the expectation that such words, unlike real words, do not activate higher cognitive processes in the brain. However, other theories assume that pseudowords are perceived as new words, leading to an even higher cognitive response. The aim of this study was to investigate the cognitive load of processing a pseudoword by observing event-related potentials in a 3-stimulus oddball paradigm using real target words, real non-target words, and pseudowords as oddball stimuli. The results show a clear task-related P3b triggered by target words, but also a prominent P600 component triggered by pseudowords, indicating difficulty in the classification task due to unknown words. Surprisingly, N400 was decreased for pseudowords compared to target and non-target words at the locations where P3b and P600 were observed, suggesting that task-related effects might inhibit other aspects of cognitive processing. These results could lead to better understanding of the components that may overlap temporally and topographically, and to the more precise control of different cognitive generators involved in event-related potential experiments in pseudowords.

Erroneous Word-Stress Patterns Used by EFL Yemeni Learners

This experimental study aims at investigating the English word-stress patterns used by Yemenis, learning English as a foreign language, and the erroneous stress patterns used by them. Accent or stress is a feature of high significance in English speech. At the level of a word, one syllable gets accentuated with primary stress. To achieve the purpose of this study, and to find out to what extent word stress of Received Pronunciation English poses difficulty on Yemeni Arabic speakers using English as a foreign language, 120 subjects of various scientific disciplines, were chosen for data collection. They were recorded and their utterances went through deep analysis based on the auditory impression of the researcher and on the spectrographic evidence resulting from the speech analysis of the software program PRAAT. The most significant findings reached by the researcher were that word-stress in the four-syllable target words were the most problematic for the speakers in which 53.2% of them put the stress, randomly, on the wrong syllables in words. Three-syllable target words appeared to be less problematic as 44.4% of the participants placed the stress inaccurately in words. The least difficulties encountered by the speakers were with the two-syllable target words where 70.6% of the speakers managed to pronounce the words with correct stress placement. It is noteworthy to mention that there was a tendency among the speakers who produced wrong stress patterns, to accent either the first syllable or the one including a long vowel or a diphthong in the words.

Does writing words in notes contribute to vocabulary learning?

There has been little research investigating the effects of notetaking on foreign language (FL) learning, and no studies have examined how it affects vocabulary learning. The present study investigated the vocabulary written in notes of 86 students after they had listened to a teacher in an English as a foreign language (EFL) class. The results showed that 51.2% of participants took notes, and 32.6% wrote information about target words in notes. However, there were only 95 instances of information written about the 28 target words. The results revealed that the odds of vocabulary learning were 15 and 10 times higher in the immediate and delayed posttests for target words that were written in notes. The analysis also indicated that the use of first language (L1) translation in teacher speech increased the chances that target words were written in notes, and that writing words in notes was the most effective predictor of learning.

The Effect of Multiplayer Video Games on Incidental and Intentional L2 Vocabulary Learning: The Case of Among Us

Vocabulary learning has been traditionally considered central to second language learning. It may take place either intentionally, by means of deliberate attempts to commit factual information to memory, or incidentally, as a consequence of other cognitive processes involving comprehension. Video games, which have been extensively employed in educational contexts to understand lexical development in foreign languages, foster both exposure to and the production of authentic and meaning-focused vocabulary. An empirical study was conducted to explore the effect of playing an online multiplayer social deduction game (i.e., a game in which players attempt to uncover each other’s hidden role) on incidental and intentional second language (L2) vocabulary learning. Secondary school pre-intermediate English as a Foreign Language (EFL) students (n = 54) took a vocabulary pre-test that identified eight unknown words likely to appear in the video game Among Us. Then, students were randomly assigned to different groups of players and to different learning conditions—within each group, half of the players were given a list of phrases containing such target words, which they were encouraged to meaningfully use in the game by means of written interaction. In doing so, students learnt some target words intentionally and provided contextualized incidental exposure to other players. They took a vocabulary test after two sessions of practice with the game to explore intentional and incidental L2 vocabulary learning gains. The pre- and post-tests suggested, among other results, that players using new L2 words in the game Among Us would retain more vocabulary than players only encountering them, that vocabulary intentionally input helped other users trigger incidental vocabulary learning, and that repetition had a positive effect on L2 vocabulary learning.

Understanding Child-Directed Speech Around Book Reading in Toddler Classrooms: Evidence From Early Head Start Programs

Child-directed speech (CDS), which can help children learn new words, has been rigorously studied among infants and parents in home settings. Yet, far less is known about the CDS that teachers use in classrooms with toddlers and children’s responses, an important question because many toddlers, particularly in high-need communities, attend group-care settings. This exploratory study examines the linguistic environment during teacher-led book readings in American Early Head Start classrooms serving 2-year-olds from households in poverty. Seven teachers in four classrooms were trained to emphasize target words while reading story and informational books. We first analyzed the nature and quality of their book readings from a macro-level, exploring global instructional quality [Classroom Assessment Scoring System (CLASS)] and linguistic complexity [i.e., diversity of vocabulary (D) and sophistication of syntax (MLU-w)], and we also examined micro-level teacher-child talk strategies and use of target words. Compared to prior research, these classrooms had similar global quality and syntactic complexity, although less lexical diversity. Exploratory results also revealed three distinct teacher talk patterns—teachers who emphasized (1) comments, (2) questions, and (3) a balance of the two. Question-focused teachers had more adult and child talk during reading, as well as more repetitions of target words, and stronger CLASS Engaged Support for Learning. However, comment-focused teachers used more diverse vocabulary and had stronger CLASS Emotional and Behavioral Support. Results illuminate the nature and quality of CDS in toddler classrooms, particularly in the context of an intervention emphasizing target vocabulary words, and highlight applications for professional development and questions for further research.

Vocabulary development through reading: A comparison of approaches

<p>This thesis compares two approaches to extensive reading to determine the extent that they facilitate vocabulary development. The first approach is a traditional reading-only approach, and the second approach is a task-based approach which supplements reading with post-reading meaning-focused discussions. These two approaches are compared using a battery of tests, most notably a measure for productive knowledge of word associations. For years, scholars have believed that word associations have potential to reveal important information about a person’s language proficiency. One reason word associations are intriguing is that a large amount of a person’s lexicon can be assessed (Meara, 2009). This is possible because a large amount of data from the learner can be gathered in a short period of time. Another intriguing aspect of word association data is that it is one aspect of vocabulary knowledge that is not based on correct performance. This raises the question of an appropriate means of assigning value to the associations, a question which still hinders research to this day. Recent research has made progress in this area with a multi-level taxonomy (i.e., Fitzpatrick, 2007), creating a picture of the types of associations which exist in a learner’s lexicon. However, this taxonomy does not address the strength of the association. Wilks and Meara (2007) have attempted to tackle association strength through the use of self-report measures, whereby a test-taker reports strength of association on a four-point scale from weak to strong. This has left them with "...problems which we have not yet solved, notably a tendency for some test takers to claim that most associations are strong, while others appear to be very reluctant to identify strong associations..." (Meara, 2009, p. 80). In other words, the question of how to appropriately determine association strength is still unanswered. In the current study lexical development, in the form of word association knowledge, was measured using a multi-response word association test. Participants were assessed on their knowledge of 60 target words which occurred in five graded readers that they read over the course of the study. The learners first self-reported their knowledge of the 60 target words in terms of no knowledge, form knowledge, or meaning knowledge. The students provided up to five associations for each word that they reported at either the form or meaning levels. They did this once before reading the five graded readers, and again after finishing the graded readers. The associations provided by the students were analyzed using Latent Semantic Analysis, a method for computing semantic similarity between words (Landauer & Dumais, 1997). The associations a learner provided for each target word were assigned a similarity value representing how similar they were to the target word to which they were provided. The hypothesis was that the students who engaged in the post-reading discussion activities would show greater increases in associational knowledge of the target words than those students who did not participate in the discussions. The major finding from this thesis was that the students who struggled with a word during the post-reading discussion and were provided an opportunity to discuss the word with their group developed associational knowledge to a significantly greater degree than those students who did not encounter the words during the discussions. This emphasizes the facilitative role that meaning-focused output activities have on vocabulary development. In addition, the associational knowledge developed at the initial stages of word learning (i.e., from no knowledge to form knowledge), continued to develop from form knowledge of a word to meaning knowledge of the word, and was also developing even when words did not change in reported knowledge. This suggests a continual restructuring of the learners’ lexicon, exemplifying past research (e.g., Henriksen, 1999). Overall, the findings suggest that an extensive reading approach which includes opportunities for meaning-focused interaction has greater benefits for lexical development when compared to a traditional reading-only approach to extensive reading.</p>

Vocabulary development through reading: A comparison of approaches

<p>This thesis compares two approaches to extensive reading to determine the extent that they facilitate vocabulary development. The first approach is a traditional reading-only approach, and the second approach is a task-based approach which supplements reading with post-reading meaning-focused discussions. These two approaches are compared using a battery of tests, most notably a measure for productive knowledge of word associations. For years, scholars have believed that word associations have potential to reveal important information about a person’s language proficiency. One reason word associations are intriguing is that a large amount of a person’s lexicon can be assessed (Meara, 2009). This is possible because a large amount of data from the learner can be gathered in a short period of time. Another intriguing aspect of word association data is that it is one aspect of vocabulary knowledge that is not based on correct performance. This raises the question of an appropriate means of assigning value to the associations, a question which still hinders research to this day. Recent research has made progress in this area with a multi-level taxonomy (i.e., Fitzpatrick, 2007), creating a picture of the types of associations which exist in a learner’s lexicon. However, this taxonomy does not address the strength of the association. Wilks and Meara (2007) have attempted to tackle association strength through the use of self-report measures, whereby a test-taker reports strength of association on a four-point scale from weak to strong. This has left them with "...problems which we have not yet solved, notably a tendency for some test takers to claim that most associations are strong, while others appear to be very reluctant to identify strong associations..." (Meara, 2009, p. 80). In other words, the question of how to appropriately determine association strength is still unanswered. In the current study lexical development, in the form of word association knowledge, was measured using a multi-response word association test. Participants were assessed on their knowledge of 60 target words which occurred in five graded readers that they read over the course of the study. The learners first self-reported their knowledge of the 60 target words in terms of no knowledge, form knowledge, or meaning knowledge. The students provided up to five associations for each word that they reported at either the form or meaning levels. They did this once before reading the five graded readers, and again after finishing the graded readers. The associations provided by the students were analyzed using Latent Semantic Analysis, a method for computing semantic similarity between words (Landauer & Dumais, 1997). The associations a learner provided for each target word were assigned a similarity value representing how similar they were to the target word to which they were provided. The hypothesis was that the students who engaged in the post-reading discussion activities would show greater increases in associational knowledge of the target words than those students who did not participate in the discussions. The major finding from this thesis was that the students who struggled with a word during the post-reading discussion and were provided an opportunity to discuss the word with their group developed associational knowledge to a significantly greater degree than those students who did not encounter the words during the discussions. This emphasizes the facilitative role that meaning-focused output activities have on vocabulary development. In addition, the associational knowledge developed at the initial stages of word learning (i.e., from no knowledge to form knowledge), continued to develop from form knowledge of a word to meaning knowledge of the word, and was also developing even when words did not change in reported knowledge. This suggests a continual restructuring of the learners’ lexicon, exemplifying past research (e.g., Henriksen, 1999). Overall, the findings suggest that an extensive reading approach which includes opportunities for meaning-focused interaction has greater benefits for lexical development when compared to a traditional reading-only approach to extensive reading.</p>