Linguistic Feature Extraction Research Articles

Job matching analysis by latent semantic indexing enhanced on multilingual word meanings

Job matching is a hiring process that involves a thorough understanding of the context and meaning of words in different languages. The updated and expanded latent semantic indexing (LSI) Framework seeks to improve the precision and relevance of job matching analysis of word meanings in multi-languages. Because they only compare related terms, conventional LSIs are often insufficient to address the complexity of context in job matching. Extending the LSI approach can improve the vector representation of words and help you understand the context and semantic relationships in the text. Improved LSI analyzes context more precisely by using word vector representation. Improved LSI focuses on understanding semantic relationships between words in many languages to produce more accurate and relevant job matches. This paper describes the steps involved in improving LSI, such as data collection, pre-processing, linguistic feature extraction, LSI model training, and evaluation of matching results. The results show that the examined classification model has much better performance in terms of word classification. Conventional LSI has an average prediction value of 79%, once the enhanced LSI can accurately predict about 84% of the entire word, it has a reasonable capacity to recognize the actual words in a natural context.

A Unified Graph Theory Approach: Clustering and Learning in Criminal Data

Crime report clustering plays a critical role in modern law enforcement, enabling the identification of patterns and trends essential for proactive policing. However, traditional clustering approaches face significant challenges with the complex, unstructured nature of crime reports and their inherent sparse relationships. While graph-based clustering shows promise, issues of noise sensitivity and data sparsity persist. This study introduces a unified approach integrating spectral graph-based clustering with Graph Convolutional Networks (GCN) to address these challenges. The proposed approach encompasses data collection, preprocessing, linguistic feature extraction, vectorization, graph construction, graph learning, and clustering to effectively capture the intricate similarities between crime reports. The proposed approach achieved significant improvements over existing methods: a Silhouette Score of 0.77, a Davies–Bouldin Index of 0.51, and consistent performance across varying dataset sizes (100–1000 nodes). These results demonstrate the potential for enhanced crime pattern detection in law enforcement operations.

An Exploration of the Precision Path of Integrating Artificial Intelligence Technology into Japanese Literature Education

Abstract With the further spread of Japanese literature, this paper explores the application of artificial intelligence technology in Japanese literature education, improves the feature extraction TF-IDF algorithm based on information theory, counts the information content of the keywords as the control coefficient of their TF-IDF values in the final result, and constructs the TFIDF-BOIT linguistic feature extraction algorithm for Japanese literary works. The style analysis of literary works was conducted by screening five-dimensional variables based on the extracted linguistic features. A more targeted teaching path is proposed by analyzing the language features and styles of various Japanese literary works. The DR in Japanese literature during the Nara period was 0.345, and the DLS was 0.472. While in the Meiji period, the DR in literature decreased by 0.104, and the DLS increased by 0.085. The refinement of literature education can be achieved through the intelligent analysis of Japanese literature.

Hierarchical graph-based text classification framework with contextual node embedding and BERT-based dynamic fusion

We propose a novel hierarchical graph-based text classification framework that leverages the power of contextual node embedding and BERT-based dynamic fusion to capture the complex relationships between the nodes in the hierarchical graph and generate a more accurate classification of text. The framework consists of seven stages: Linguistic Feature Extraction, Hierarchical Node Construction with Domain-Specific Knowledge, Contextual Node Embedding, Multi-Level Graph Learning, Dynamic Text Sequential Feature Interaction, Attention-Based Graph Learning, and Dynamic Fusion with BERT. The first stage, Linguistic Feature Extraction, extracts the linguistic features of the text, including part-of-speech tags, dependency parsing, and named entities. The second stage constructs a hierarchical graph based on the domain-specific knowledge, which is used to capture the relationships between nodes in the graph. The third stage, Contextual Node Embedding, generates a vector representation for each node in the hierarchical graph, which captures its local context information, linguistic features, and domain-specific knowledge. The fourth stage, Multi-Level Graph Learning, uses a graph convolutional neural network to learn the hierarchical structure of the graph and extract the features of the nodes in the graph. The fifth stage, Dynamic Text Sequential Feature Interaction, captures the sequential information of the text and generates dynamic features for each node. The sixth stage, Attention-Based Graph earning, uses an attention mechanism to capture the important features of the nodes in the graph. Finally, the seventh stage, Dynamic Fusion with BERT, combines the output from the previous stages with the output from a pre-trained BERT model to obtain the final integrated vector representation of the text. This approach leverages the strengths of both the proposed framework and BERT, allowing for better performance on the classification task. The proposed framework was evaluated on several benchmark datasets and compared to state-of-the-art methods, demonstrating significant improvements in classification accuracy.

Two End-to-End Quantum-Inspired Deep Neural Networks for Text Classification

In linguistics, the uncertainty of context due to polysemy is widespread, which attracts much attention. Quantum-inspired complex word embedding based on Hilbert space plays an important role in natural language processing (NLP), which fully leverages the similarity between quantum states and word tokens. A word containing multiple meanings could correspond to a single quantum particle which may exist in several possible states, and a sentence could be analogous to the quantum system where particles interfere with each other. Motivated by quantum-inspired complex word embedding, interpretable complex-valued word embedding (ICWE) is proposed to design two end-to-end quantum-inspired deep neural networks (ICWE-QNN and CICWE-QNN representing convolutional complex-valued neural network based on ICWE) for binary text classification. They have the proven feasibility and effectiveness in the application of NLP and can solve the problem of text information loss in CE-Mix [1] model caused by neglecting the important linguistic features of text, since linguistic feature extraction is presented in our model with deep learning algorithms, in which gated recurrent unit (GRU) extracts the sequence information of sentences, attention mechanism makes the model focus on important words in sentences and convolutional layer captures the local features of projected matrix. The model ICWE-QNN can avoid random combination of word tokens and CICWE-QNN fully considers textual features of the projected matrix. Experiments conducted on five benchmarking classification datasets demonstrate our proposed models have higher accuracy than the compared traditional models including CaptionRep BOW, DictRep BOW and Paragram-Phrase, and they also have great performance on F1-score. Eespecially, CICWE-QNN model has higher accuracy than the quantum-inspired model CE-Mix as well for four datasets including SST, SUBJ, CR and MPQA. It is a meaningful and effictive exploration to design quantum-inspired deep neural networks to promote the performance of text classification.

Net activism and whistleblowing on YouTube: a text mining analysis.

Social media is more and more dominant in everyday life for people around the world. YouTube content is a resource that may be useful, in social computational science, for understanding key questions about society. Using this resource, we performed web scraping to create a dataset of 644,575 video transcriptions concerning net activism and whistleblowing. We automatically performed linguistic feature extraction to capture a representation of each video using its title, description and transcription (downloaded metadata). The next step was to clean the dataset using automatic clustering with linguistic representation to identify unmatched videos and noisy keywords. Using these keywords to exclude videos, we finally obtained a dataset that was reduced by 95%, i.e., it contained 35,730 video transcriptions. Then, we again automatically clustered the videos using a lexical representation and split the dataset into subsets, leading to hundreds of clusters that we interpreted manually to identify a hierarchy of topics of interest concerning whistleblowing. We used the dataset to learn a lexical representation for a specific topic and to detect unknown whistleblowing videos for this topic; the accuracy of this detection is 57.4%. We also used the dataset to identify interesting context linguistic markers around the names of whistleblowers. From a given list of names, we automatically extracted all 5-g word sequences from the dataset and identified interesting markers in the left and right contexts for each name by manual interpretation. The results of our study are the following: a dataset (raw and cleaned collections) concerning whistleblowing, a hierarchy of topics about whistleblowing, the automatic prediction of whistleblowing and the semi-automatic semantic analysis of markers around whistleblower names. This text mining analysis can be exploited for digital sociology and e-democracy studies.

Optimization Prediction of Big Five Personality in Twitter Users

Various kinds of information can be acquired from social media platforms; one of them is on Twitter. User biographical information and tweets are the essential assets for research that can describe the Big Five Personality, including openness, conscientiousness, extraversion, agreeableness, and neuroticism. Several previous studies have tried the prediction of Big Five Personality. However, the authors found problems in how to optimize the work of the personality prediction system. So, in this study, Big Five Personality predictions were carried out on users of Twitter and improved the performance of the personality prediction system. We implement optimization techniques such as sampling, feature selection, and hyperparameter tuning to enhance the performance. This study also applies linguistic feature extraction, such as LIWC and TF-IDF. By using 287 Twitter users that have permitted their data to be crawled acquired from an online survey using Big Five Inventory (BFI), and applying all optimization techniques, the average accuracy result is 84.22% which is a 74.44% gain over the specified baseline.

Detecting Depression Signs on Social Media: A Systematic Literature Review.

Among mental health diseases, depression is one of the most severe, as it often leads to suicide; due to this, it is important to identify and summarize existing evidence concerning depression sign detection research on social media using the data provided by users. This review examines aspects of primary studies exploring depression detection from social media submissions (from 2016 to mid-2021). The search for primary studies was conducted in five digital libraries: ACM Digital Library, IEEE Xplore Digital Library, SpringerLink, Science Direct, and PubMed, as well as on the search engine Google Scholar to broaden the results. Extracting and synthesizing the data from each paper was the main activity of this work. Thirty-four primary studies were analyzed and evaluated. Twitter was the most studied social media for depression sign detection. Word embedding was the most prominent linguistic feature extraction method. Support vector machine (SVM) was the most used machine-learning algorithm. Similarly, the most popular computing tool was from Python libraries. Finally, cross-validation (CV) was the most common statistical analysis method used to evaluate the results obtained. Using social media along with computing tools and classification methods contributes to current efforts in public healthcare to detect signs of depression from sources close to patients.

Leveraging Twitter data to analyze the virality of Covid-19 tweets: a text mining approach

ABSTRACT As the novel coronavirus spreads across the world, work, pleasure, entertainment, social interactions, and meetings have shifted online. The conversations on social media have spiked, and given the uncertainties and new policies, COVID-19 remains the trending topic on all such platforms, including Twitter. This research explores the factors that affect COVID-19 content-sharing by Twitter users. The analysis was conducted using 57,000 plus tweets that mentioned COVID-19 and related keywords. The tweets were subjected to the Natural Language Processing (NLP) techniques like Topic modelling, Named Entity-Relationship, Emotion & Sentiment analysis, and Linguistic feature extraction. These methods generated features that could help explain the retweet count of the tweets. The results indicate that tweets with named entities (person, organisation, and location), expression of negative emotions (anger, disgust, fear, and sadness), reference to mental health, optimistic content, and greater length have higher chances of being shared (retweeted). On the other hand, tweets with more hashtags and user mentions are less likely to be shared.

A sentiment analysis approach based on exploiting Chinese linguistic features and classification

This paper proposes a novel approach to exploiting linguistic features and SVMperf algorithm based semantic classification, and this approach is applied into sentiment analysis. It uses the dependency relationship to do the linguistic feature extraction. This paper adopts χ2 (chi-square) and pointwise mutual information (PMI) metrics for feature selection. Furthermore, as for the approach on sentiment analysis, this paper uses the SVMperf algorithm to implement the alternative structural formulation of the SVM optimisation problem for classification. E-commerce datasets are used to evaluate the experiment performance. Experiment results show the feasibility of the approach. Existing problems and further works are also presented.

Computing the structure of language for neuropsychiatric evaluation

We describe recent preliminary studies demonstrating that computational analysis of spoken and written language can provide for highly accurate diagnostics over a wide variety of psychiatric and neurologic conditions, including psychosis, drug abuse, Parkinson's, and Alzheimer's. These results are based on the mathematical formalization of psychiatric qualitative knowledge related to the characterization of the conditions (e.g., “derailment” in psychosis) and drug effects (e.g., increased intimacy/affection with the use of the recreational drug ecstasy), as well as novel linguistic feature extraction approaches. Moreover, we show novel results using publicly available text sources suggesting that 1) it is possible to define an embedding space that allows modeling of the vast language dimension into a smaller space to map and compare different conditions, and 2) computational studies of a public personality (Ronald Reagan) can likely yield novel insights into normal aging and neurodegenerative disorders. Finally, we discuss the implications for mental health (and possibly, computer science) of a systematic application of this methodology, extended to include similar readily available behavioral data such as voice and video.

Social language processing: A framework for analyzing the communication of terrorists and authoritarian regimes

Social Language Processing (SLP) is introduced as an interdisciplinary approach to assess social features in communications by terrorist organizations and authoritarian regimes. The SLP paradigm represents a rapprochement of theories, tools and techniques from cognitive science, communications, computational linguistics, discourse processing, language studies and social psychology. The SLP paradigm consists of three broad stages: (1) linguistic feature identification; (2) linguistic feature extraction; and (3) classifier development. In this paper, we detail the SLP paradigm and review several linguistic features that are especially amenable to uncovering the social dynamics of groups that are difficult to assess directly (i.e. through questionnaires, interviews or direct observation). We demonstrate the application of SLP to identify status, cohesion and deception in the case of Saddam Hussein’s regime. Specifically, we analyzed the memoranda, letters and public communiqués distributed within and from Saddam Hussein’s administration in a recently recovered corpus called the Iraqi Perspectives Project, along with several related projects. We conclude with a discussion of the challenges that SLP faces for assessing social features across cultures in public and captured communications of terrorists and political regimes, along with responses to these organizations.