Analysis Dictionary Research Articles

Finding the Needle in the Haystack: Can Natural Language Processing of Students' Evaluations of Teachers Identify Teaching Concerns?

Institutions rely on student evaluations of teaching (SET) to ascertain teaching quality. Manual review of narrative comments can identify faculty with teaching concerns but can be resource and time-intensive. To determine if natural language processing (NLP) of SET comments completed by learners on clinical rotations can identify teaching quality concerns. Single institution retrospective cohort analysis of SET (n = 11,850) from clinical rotations between July 1, 2017, and June 30, 2018. The performance of three NLP dictionaries created by the research team was compared to an off-the-shelf Sentiment Dictionary. The Expert Dictionary had an accuracy of 0.90, a precision of 0.62, and a recall of 0.50. The Qualifier Dictionary had lower accuracy (0.65) and precision (0.16) but similar recall (0.67). The Text Mining Dictionary had an accuracy of 0.78 and a recall of 0.24. The Sentiment plus Qualifier Dictionary had good accuracy (0.86) and recall (0.77) with a precision of 0.37. NLP methods can identify teaching quality concerns with good accuracy and reasonable recall, but relatively low precision. An existing, free, NLP sentiment analysis dictionary can perform nearly as well as dictionaries requiring expert coding or manual creation.

Dictionary-Based Multi-View Learning With Privileged Information

Multi-view learning can improve classification performance by combining information between different views. Due to the similarity in different views of the dataset, sometimes the features obtained are highly limited and redundant. At the same time, different views accumulate a large amount of noisy information, which will affect the classification performance of the model. To solve these problems, we embed privileged information in the model and introduce dictionary learning, and proposed a new dictionary-based multi-view learning method with privileged information (MVDL-PI). First, two sets of dictionaries (synthetic dictionary and analysis dictionary) and sparse representation matrices of different information domains are obtained for each view information and privilege information through dictionary learning. Then, we obtain consistency information from the regularization terms of the two different sets of synthetic dictionaries and construct a LUPI (Learning using privileged information) classifier by the sparse representation. In addition, we use alternating convex optimization and Lagrange multiplier methods to optimize the model and prove its convergence. In the experiment, we did a number of experiments comparing this method with similar recent methods. The experimental results show that the MVDL-PI method is superior to other methods in terms of stability and classification accuracy.

"Approaches to sentiment analysis of Hungarian political news at the sentence level"

Automated sentiment analysis of textual data is one of the central and most challenging tasks in political communication studies. However, the toolkits available are primarily for English texts and require contextual adaptation to produce valid results—especially concerning morphologically rich languages such as Hungarian. This study introduces (1) a new sentiment and emotion annotation framework that uses inductive approaches to identify emotions in the corpus and aggregate these emotions into positive, negative, and mixed sentiment categories, (2) a manually annotated sentiment data set with 5700 political news sentences, (3) a new Hungarian sentiment dictionary for political text analysis created via word embeddings, whose performance was compared with other available sentiment dictionaries. (4) Because of the limitations of sentiment analysis using dictionaries we have also applied various machine learning algorithms to analyze our dataset, (5) Last but not least to move towards state-of-the-art approaches, we have fine-tuned the Hungarian BERT-base model for sentiment analysis. Meanwhile, we have also tested how different pre-processing steps could affect the performance of machine-learning algorithms in the case of Hungarian texts.

Relationship between duration of sick leave and time variation of words used in return-to-work programs for depression.

Return-to-work (RTW) programs are provided as rehabilitation for people who have taken sick leave from work because of mental health problems. However, methods to present this information to workplaces objectively remain limited. This study aimed to conduct an exploratory investigation of the relationship between duration of sick leave and time variation of words used in RTW programs for depression from textual data collected from electronic medical records as a new evaluation indicator. The study subjects were those who had taken sick leave because of major depressive or adjustment disorder and had participated in an RTW program. The study data comprised demographic characteristics and texts. Textual data were collected from electronic medical records and classified based on the SOAP note. Thereafter, the textual data were quantified into category scores based on a standard text analysis dictionary. A generalized linear mixed model was used for the statistical analysis, with the score for each category (emotional, social, cognitive, perceptual, biological, motivational, relativity, and informal) as the dependent variable and the duration of sick leave, time, and interaction between the duration of sick leave and time as the independent variables. The level of statistical significance was set at 0.05. In total, 42 participants were included in the analysis. The results revealed a significant interaction between the social (p = 0.001) and emotional (p = 0.002) categories. The findings suggest a relationship between word changes in electronic medical records and the duration of sick leave.

Word translation for Indo-Aryan languages using different retrieval techniques

<p>The study of Natural Language Processing has been revolutionized by word embedding, enabling advanced language models to understand and generate human-like text. In this research article, we delve deep into the world of word embedding, aiming to provide a comprehensive exploration of its underlying principles, methodologies, and applications. One important factor that affects many multilingual language processing activities is the word translation or incorporation of bilingual dictionaries. We used bilingual dictionaries or parallel data for translation from one language to another. For this research work, this problem is addressed, and also generating the best cross-lingual word embedding for the different language pairs. So, we are using an aligned document sentence-aligned corpus, or any bilingual dictionary for this research analysis. For the most frequent word, we are assuming that there is an intra-lingual similarity distribution, and both the source and the target corpora have a comparable distribution graph. Additionally, these embeddings are isometric. These cross-lingual word embeddings are used for cross-lingual transfer learning and unsupervised neural machine translation. This research aims to improve the accuracy and efficiency of word translation between different language pairs by employing different retrieval techniques. The study analyzes the effectiveness of these techniques on different language pairs, including English-Hindi, English-Punjabi, English-Gujarati, English-Bengali, and English-Marathi. The research is expected to contribute significantly to the field of language translation by introducing innovative methods and other applications.</p>

A weighted sparse classification method based on period analysis dictionary

The periodic transient shocks triggered by damages in rolling bearings are frequently overshadowed by disruptive elements such as noise and harmonics. Therefore, the extraction of fault characteristics from these disturbances to identify the health status of the bearing is crucial for fault diagnosis. This study presents a novel approach, the period analysis dictionary weighted sparse representation classification (PAD-WSRC) method, designed specifically for rolling bearings. The proposed approach incorporates Bi-damped wavelet as the dictionary wavelet atom, while accounting for the pulse characteristics induced by faults and leveraging prior knowledge of periodicity. A weighted sparse representation (SR) method was also designed, which calculates the weighted SR coefficients of samples, amplifying the local features of samples while addressing the impact of time-shift bias. In addition, the bearing fault type is identified using a mutual correlation classification criterion based on sparse approximation. Our PAD-WSRC strategy has demonstrated its effectiveness in classifying the health status of bearings across three datasets, achieving recognition accuracies of 99.75%, 99.69% and 99.17%, respectively. Comparisons with several traditional methods further underscore the effectiveness and superiority of our proposed method in classifying rolling bearing faults.

Interactive and discriminative analysis dictionary learning for image classification

Interactive and discriminative analysis dictionary learning for image classification

Sentiment analysis of subcutaneous and intravenous immunoglobulin therapy: public healthcare perception through social media discourse.

Immunoglobulin replacement therapy remains a cornerstone of treatment in antibody deficiencies and other inborn errors of immunity. While patient preferences between subcutaneous and intravenous immunoglobulin have been studied through questionnaires, no study has yet explored patient perspectives in a free environment. Therefore, we aimed to conduct a sentiment analysis as well as a temporal and geographical analysis on public opinions obtained from social media to better understand patient satisfaction and public perception on immunoglobulin therapy. A dataset of 43,700 tweets spanning from the 1st of January of 2012 to the 31st of December of 2022 was obtained. A Valence Aware Dictionary for Sentiment Reasoning sentiment analysis was performed, followed by statistical, geographical and temporal analyses. Mean polarity of intravenous immunoglobulin related tweets was 0.1295 (positive), while mean polarity for subcutaneous immunoglobulin was 0.2117 (positive). Temporal analysis through a statistical model demonstrated that the volume of tweets increased over time for both subcutaneous and intravenous treatment. Geographical analysis revealed that the majority of texts originated from the United States. The highest mean polarity was observed in Romania with a mean value of 0.2966, while the lowest polarity was documented in Norway with a mean of -0.0211. Tweets linked to subcutaneous immunoglobulin treatment had a higher average polarity, indicating a more positive public perception. The amount of tweets relating to both therapies showed a tendency to increase as the years progressed, implying an increase in public discussion on immunoglobulin treatment.

Discriminative Dictionary Pair Learning With Scale-Constrained Structured Representation for Image Classification.

The dictionary pair learning (DPL) model aims to design a synthesis dictionary and an analysis dictionary to accomplish the goal of rapid sample encoding. In this article, we propose a novel structured representation learning algorithm based on the DPL for image classification. It is referred to as discriminative DPL with scale-constrained structured representation (DPL-SCSR). The proposed DPL-SCSR utilizes the binary label matrix of dictionary atoms to project the representation into the corresponding label space of the training samples. By imposing a non-negative constraint, the learned representation adaptively approximates a block-diagonal structure. This innovative transformation is also capable of controlling the scale of the block-diagonal representation by enforcing the sum of within-class coefficients of each sample to 1, which means that the dictionary atoms of each class compete to represent the samples from the same class. This implies that the requirement of similarity preservation is considered from the perspective of the constraint on the sum of coefficients. More importantly, the DPL-SCSR does not need to design a classifier in the representation space as the label matrix of the dictionary can also be used as an efficient linear classifier. Finally, the DPL-SCSR imposes the l2,p -norm on the analysis dictionary to make the process of feature extraction more interpretable. The DPL-SCSR seamlessly incorporates the scale-constrained structured representation learning, within-class similarity preservation of representation, and the linear classifier into one regularization term, which dramatically reduces the complexity of training and parameter tuning. The experimental results on several popular image classification datasets show that our DPL-SCSR can deliver superior performance compared with the state-of-the-art (SOTA) dictionary learning methods. The MATLAB code of this article is available at https://github.com/chenzhe207/DPL-SCSR.

PECULIARITIES OF ENGLISH AND UKRAINIAN ZOOPHRASES: СOMPARATIVE ASPECT

The article deals with the peculiarities English and Ukrainian zoophrasemic specification. It is well known, that any fixed phrase has its own special meaning, which is often impossible to deduce from the meanings of separate words. The comparative – confrontation studies of zoophrases and their world models makes it also possible to solve a number of complicated problems in the field of translation. The topicality of the study of theoretical is specified by insufficient study of theoretical and methodological problems of semantics in comparative – confrontation phraseology as well as the lock of information, coming to light from the results of a more profound analysis of English-Ukrainian correspondences and divergencies. The empirical material under study. For obtaining as precise research data as possible 100 most frequently used phrases enclosing the same number of living creature names with their zoophrasemic specificity have been extracted from different sources in English and Ukrainian. The aim of writing the article is from the view-point of modern achievements in learning comparative phraseology and the arosen new paradigms of cognitive science to characterize that aspect of different set phrases that are based on both coincidences and divergences in the perception of the world around by English and Ukrainian native speakers. The following methods of linguistic research have been applied: phraseological identification, the description and analysis dictionary definitions with selective references to lexicographic and literary sources, classifying them according to different categories. The results of the study is an attempt to demonstrate phrasemic potency in the domain of naming living creatures in English and Ukrainian. Closely and distantly related other languages and their variants may be the subject – matter of further zoophrasemic studies.

Public’s perception on nursing education during the COVID-19 pandemic: SENTIMENT analysis of Twitter data

With the emergence of nurses as heroes on the front lines during the COVID-19 pandemic, posts on Twitter about nursing and nursing education began to increase. This study aims to make a sentiment analysis on Twitter posts regarding society's perception of nursing education during the COVID-19 pandemic and to shed light on concerns, sentiments, and experiences related to nursing education during the pandemic. The text mining method was used to analyze the sentiment analysis of Twitter data. Between July 1st, 2021, and July 1st, 2022, during the COVID-19 pandemic, a total of 30,194. Twitter messages in English were analyzed using the “nursing education” hashtag and keyword. All data cleaning and analysis were carried out with R software, and the tweet data set was analyzed using the frequency of keywords and sentiment analysis. Sentiment analysis of each tweet was conducted using various sentiment analysis dictionaries. The results showed that nursing, education, health, school, and nurses were the most used keywords. In the sentiment analysis conducted during the pandemic, 84 % of the tweets comprised positive, 12 % negative, and 4 % neutral sentiments. The conclusions highlight the importance of knowing and appreciating the contributions of nurses and nursing students during the pandemic and supporting more nurse professionals during crises such as the COVID-19 pandemic by addressing the problems during nursing education.

Perceiving with strangeness: quantifying a style of altered consciousness as estrangement in a corpus of 1960s American science fiction

Abstract In 1960s American science fiction, representations of altered consciousness may function as a novum, framing how protagonists perceive and interact with the storyworld, motivating their actions, and estranging readers. Representations of these states are rooted in the lexical particulars of style, which became of central concern to the rising New Wave subgenre. As a result of the defamiliarized focalization of altered consciousness, estranged readers confront in fresh ways core sociocultural concerns of the era embedded in the thematics of the novels. For this reason, it is fruitful to ask how the language of altered consciousness can be characterized. What lexical elements defamiliarize the focalization giving rise to estrangement? This paper addresses this question through a computational literary linguistic approach. Quantifying the lexical composition of altered states with content analysis dictionaries and performing cluster analysis uncovers underlying similarities within a corpus of 1960s American science fiction novels. The language of altered consciousness is then identified as a language of estrangement through stylistic close reading. This provides one route into understanding how a novum may be constructed of language, estrange the reader, and prompt reexamination of the formerly familiar through staying with strangeness.

Two-Stage Sentiment Analysis on Indonesian Online News Using Lexicon-Based

The image of a supplier company is often associated with the well-known brand it supplies, and its reputation can be influenced by online news circulation. To maintain a positive image, it is crucial for the company to monitor and manage online news to rectify any false information. Failure to maintain a good company image can lead to customer order loss and even company shutdown. This paper aims to conduct a two-stage sentiment analysis on Indonesian news articles regarding unilateral layoffs by company XYZ. The first stage will analyze sentiment in the circulating news about the layoffs, while the second stage will assess sentiment after the company releases a press release to provide accurate information. The VADER lexicon-based method, utilizing the InSet and SentiStrength_ID Indonesian dictionaries, will be employed to analyze sentiment before and after the press release. This will enable us to compare sentiment and evaluate the effectiveness of the press release and the Indonesian dictionaries in analyzing sentiment in the news. The research findings indicate that the company's press release, aimed at correcting false information, had a positive impact by reducing negative sentiment and generating a more positive sentiment in the second stage. Moreover, the selection of the sentiment analysis dictionary also plays a critical role in determining the sentiment analysis results.

Hierarchical Domain Adaptation Projective Dictionary Pair Learning Model for EEG Classification in IoMT Systems

Epilepsy recognition based on electroencephalogram (EEG) and artificial intelligence technology is the main tool of health analysis and diagnosis in Internet of medical things (IoMT). As a distributed learning framework, federated learning can train a shared model from multiple independent edge nodes using local data, which has greatly promoted the development of IoMT. One of the main challenges of EEG-based epilepsy recognition in IoMT is that EEG records show varying distributions in different devices, different times, and different people. This nonstationary characteristic of EEG reduces the accuracy of the recognition model. To improve the classification performance in IoMT, a hierarchical domain adaptation projective dictionary pair learning (HDA-PDPL) model is developed in the study. HDA-PDPL integrates EEG signals from different domains (person, edge nodes, devices, etc.) into a set of hierarchical subspace and simultaneously learns synthesis and analysis dictionary pairs in each layer. Specifically, a nonlinear transform function is introduced to seek hierarchical feature projection. The domain adaptation term on sparse coding builds a connection between different domains. Thus, the shared synthesis and analysis dictionaries can encode domain-invariant representation and discrimination knowledge from different domains. Besides, the local preserved term of projective codes is introduced to capture the potential discriminative local structures of samples. The experimental results on two EEG epilepsy classifications verified that the HDA-PDPL model can outperform other comparisons by utilizing more shared knowledge of different domains.

Subject-Independent EEG Emotion Recognition Based on Genetically Optimized Projection Dictionary Pair Learning.

One of the primary challenges in Electroencephalogram (EEG) emotion recognition lies in developing models that can effectively generalize to new unseen subjects, considering the significant variability in EEG signals across individuals. To address the issue of subject-specific features, a suitable approach is to employ projection dictionary learning, which enables the identification of emotion-relevant features across different subjects. To accomplish the objective of pattern representation and discrimination for subject-independent EEG emotion recognition, we utilized the fast and efficient projection dictionary pair learning (PDPL) technique. PDPL involves the joint use of a synthesis dictionary and an analysis dictionary to enhance the representation of features. Additionally, to optimize the parameters of PDPL, which depend on experience, we applied the genetic algorithm (GA) to obtain the optimal solution for the model. We validated the effectiveness of our algorithm using leave-one-subject-out cross validation on three EEG emotion databases: SEED, MPED, and GAMEEMO. Our approach outperformed traditional machine learning methods, achieving an average accuracy of 69.89% on the SEED database, 24.11% on the MPED database, 64.34% for the two-class GAMEEMO, and 49.01% for the four-class GAMEEMO. These results highlight the potential of subject-independent EEG emotion recognition algorithms in the development of intelligent systems capable of recognizing and responding to human emotions in real-world scenarios.

Women Entrepreneurs Who Break through in Reward-Based Crowdfunding: The Influence of Entrepreneurial Orientation

Based upon social identity theory, having a strategic entrepreneurial orientation is crucial for ventures seeking funding, since entrepreneurial orientation (viewed as an entrepreneurial organizational culture) has a significant influence on investors’ decision-making for resource allocation. However, the attitude of investors toward women entrepreneurs’ behavioral orientation is controversial. Women entrepreneurs may not benefit from specific behavioral orientations because of gender bias. In this study, we had a sample of 5105 ‘design and technology’ campaigns with explicit gender information on Kickstarter, utilizing a computer-aided text analysis dictionary of entrepreneurial orientation to examine whether the five dimensions of entrepreneurial orientation signals affected the relationship between women entrepreneurs and their performance in reward-based crowdfunding. Our findings demonstrated that investors tended to support women entrepreneurs who displayed many of the signals for autonomy and risk-taking, while backers were skeptical of women entrepreneurs displaying a high number of the signals for proactiveness. This study will enable an in-depth understanding of the link between investors’ decision-making and women’s entrepreneurial behaviors, in addition to determining which specific entrepreneurial behavior is important for helping women entrepreneurs to obtain funding in the context of reward-based crowdfunding, from a practical perspective.

Discriminative analysis dictionary learning with adaptively ordinal locality preserving

Dictionary learning has found broad applications in signal and image processing. By adding constraints to the traditional dictionary learning model, dictionaries with discriminative capability can be obtained which can deal with the task of image classification. The Discriminative Convolutional Analysis Dictionary Learning (DCADL) algorithm proposed recently has achieved promising results with low computational complexity. However, DCADL is still limited in classification performance because of the lack of constraints on dictionary structures. To solve this problem, this study introduces an adaptively ordinal locality preserving (AOLP) term to the original model of DCADL to further improve the classification performance. With the AOLP term, the distance ranking in the neighborhood of each atom can be preserved, which can improve the discrimination of coding coefficients. In addition, a linear classifier for the classification of coding coefficients is trained along with the dictionary. A new method is designed specifically to solve the optimization problem corresponding to the proposed model. Experiments are performed on several commonly used datasets to show the promising results of the proposed algorithm in classification performance and computational efficiency.

Manifolds-Based Low-Rank Dictionary Pair Learning for Efficient Set-Based Video Recognition

As an important research direction in image and video processing, set-based video recognition requires speed and accuracy. However, the existing static modeling methods focus on computational speed but ignore accuracy, whereas the dynamic modeling methods are higher-accuracy but ignore the computational speed. Combining these two types of methods to obtain fast and accurate recognition results remains a challenging problem. Motivated by this, in this study, a novel Manifolds-based Low-Rank Dictionary Pair Learning (MbLRDPL) method was developed for a set-based video recognition/image set classification task. Specifically, each video or image set was first modeled as a covariance matrix or linear subspace, which can be seen as a point on a Riemannian manifold. Second, the proposed MbLRDPL learned discriminative class-specific synthesis and analysis dictionaries by clearly imposing the nuclear norm on the synthesis dictionaries. The experimental results show that our method achieved the best classification accuracy (100%, 72.16%, 95%) on three datasets with the fastest computing time, reducing the errors of state-of-the-art methods (JMLC, DML, CEBSR) by 0.96–75.69%.

Joint structured constraint discriminant analysis dictionary learning for pattern classification

Analysis dictionary learning (DL) has been successfully applied to the field of pattern classification. However, it is still a challenge to utilize the local structure information and the class information of samples to improve the discrimination capability of analysis dictionary. We proposed a joint structured constraint discriminant analysis DL (ADL) method (JSCDADL) to learn a structured discriminant analysis dictionary by combining the local structure information and the structured information of samples. Specifically, we first designed an adaptive local structure preserving term (ALSPT) to improve the discrimination capability of analysis dictionary. It adaptively transmits the local structure information of samples to analysis dictionary, which ensures that the same class of samples has similar sparse codes under the action of the analysis dictionary. Then, we designed a discriminative sparse coding error term that forces the coding coefficient matrix to have the desired block diagonal structure. To further enhance the discrimination capability of analysis dictionary, we designed an analysis dictionary combination term by constantly approximating the two analysis dictionaries learned to obtain an analysis dictionary with the local structure information and the structured information of samples. Moreover, we designed an effective iterative algorithm to solve the optimization problem of JSCDADL. Extensive experimental results on six datasets demonstrate that JSCDADL can achieve satisfactory classification performance compared with some state-of-the-art methods.

Noise-related face image recognition based on double dictionary transform learning

The existing single dictionary learning algorithms are applied to face recognition and achieve satisfactory results. However, their performance is poor when dealing with noisy images and images involving complex variations such as large pose variations and occlusions. In this paper, a novel noise-related face image recognition method based on double dictionary transform learning (DDTL) is proposed. On the one hand, DDTL introduces the L2,p-norm to remove the redundant information in the dictionary and the noise involved in the training images, which makes the learned dictionary more discriminative. On the other hand, DDTL introduces the analysis dictionary and performs double dictionary transform learning with the synthetic dictionary. This can better reveal the relationship between the samples and the representation coefficients, and improve the accuracy of the learned dictionary and representation coefficients. Besides, DDTL introduces a linear regression term in the model learning process, which can distinguish and expand the differences between classes. Experimental results on six databases show that DDTL is superior to existing methods.