Text Mining Technology Research Articles

Using sentiment analysis to study the relationship between subjective expression in financial reports and company performance.

In recent years, with the development and progress of text information research, the disclosure of non-financial and qualitative information has often be found to have an incremental function. Financial reports, including financial statements and other relevant information, provide important insights on an enterprise’s financial status, operating results, and cash flow. Faced with a large number of financial reports, readers often do not know where to start, and as financial statements are prepared based on past transactions, they cannot fully reflect the past, present, and future economic conditions of the company. Information asymmetry and uncertainty make the text mining of financial reports of great significance to enterprise stakeholders. Accordingly, this paper takes financial reports as the research object and builds a research framework on the relationship between subjective expression in financial reports and company performance. Through natural language processing, sentiment analysis, and other text-mining technologies, the paper quantifies the subjective expression in financial reports and introduces intermediaries. Variables, moderating variables, and control variables are used to construct a multiple regression model. The empirical results show that the underlying emotional tendencies in subjective expressions substantially impact on the future development of listed companies. This paper enriches understanding of the multi-dimensional relationship between financial report text and company performance, and provides ideas for further exploring this relationship. It is of great practical significance to help them make rational decisions and ensure the normal operation of the company and the preservation and appreciation of capital.

The Identification and Dissemination of Creative Elements of New Media Original Film and Television Works Based on Review Text Mining and Machine Learning

With the continuous growth of the film market and the consumption demand of audiences, the value of film content has become increasingly apparent. Extracting movie content elements is an important step in quantitative analysis of movie content. In this paper, based on text mining technology, deep data analysis of movie reviews is carried out using TF-IDF and machine learning to visualize high-frequency words, and sentiment analysis is performed on reviews to find out the hidden deep information behind the big data of movie reviews. Although the extracted keywords can draw the content and characteristics of the film for us, they cannot establish the correlation with the creative elements of the film and television works. Therefore, in this paper, the extracted keywords are clustered to find the central words of these words. First of all, in order to improve the representativeness of keywords, the Epoch data set and the Batchsize data set are used to conduct experimental analysis on the model in this paper. Through comparative experiments, it is concluded that when Batchsize = 32 and Epoch = 25, the model achieves the optimal classification effect. The analysis shows that when the training times are too small, the model is not fully learned, and when the training times are too many, the model will be overfitted, which will reduce the accuracy of the model, resulting in the opposite effect. The keywords extracted above can draw the content and characteristics of the movie for us.

Study on Interactive Relations between Enterprise Social Media and Decision Style Based on a vector Autoregressive Model

Abstract in the network technology increasingly innovation, weibo social media such as WeChat gradually become people thought together and important platform of communication, both theoretical knowledge and practical case studies, have proved that social media can be intuitive show people the focus of the current problems, to provide effective basis for market development and investment decisions. Especially in the comprehensive promotion of text mining technology, topic extraction related to corporate social media has been reasonably applied in the financial market. However, due to the problems of sparse and unstructured data, topic extraction in practical application has become the main subject explored by researchers and scholars. This paper studies enterprise microblogging social media, for example, using both the theme of the text content and platform interactive method, according to the relations between the two kinds of typical weibo relation and the matrix, and by using two consecutive nonnegative matrix decomposition process is analyzed, finally the corresponding distance as a result, and extracting keywords to express the relationship. The actual verification results show that the clustering accuracy and theme similarity of this method are more effective than traditional theme extraction methods in corporate social media.

Dynamic sentiment sensing of cities with social media data

PurposeA lot of people share their living or travelling experiences about cities by writing posts on social media. Such posts carry multi-dimensional information about the characteristics of cities from the public’s perspective. This paper aims at applying text mining technology to automatically extract city images, which are known as how observers perceive the status of the city, from these social media texts.Design/methodology/approachThis paper proposes a data processing pipeline for automatic city image extraction and applies sentiment analysis, timing analysis and contrastive analysis in a case study on Wuhan, a central China megacity. Specifically, the city image constructed with social media text and the expected policy outcomes by the government are compared.FindingsResults reveal gaps between the public’s impression and the strategic goals of the government in traffic and environment.Originality/valueThis study contributes a novel approach to assess government performance by complementary data from social media. This case study implies the value of social media-based city image in the identification of gaps for the optimization of government performance.

Sentiment Analysis: An ERNIE-BiLSTM Approach to Bullet Screen Comments.

Sentiment analysis is one of the fields of affective computing, which detects and evaluates people’s psychological states and sentiments through text analysis. It is an important application of text mining technology and is widely used to analyze comments. Bullet screen videos have become a popular way for people to interact and communicate while watching online videos. Existing studies have focused on the form, content, and function of bullet screen comments, but few have examined bullet screen comments using natural language processing. Bullet screen comments are short text messages of different lengths and ambiguous emotional information, which makes it extremely challenging in natural language processing. Hence, it is important to understand how we can use the characteristics of bullet screen comments and sentiment analysis to understand the sentiments expressed and trends in bullet screen comments. This study poses the following research question: how can one analyze the sentiments ex-pressed in bullet screen comments accurately and effectively? This study mainly proposes an ERNIE-BiLSTM approach for sentiment analysis on bullet screen comments, which provides effective and innovative thinking for the sentiment analysis of bullet screen comments. The experimental results show that the ERNIE-BiLSTM approach has a higher accuracy rate, precision rate, recall rate, and F1-score than other methods.

Using text mining to establish knowledge graph from accident/incident reports in risk assessment

To clarify the risk factors and propagation characteristics affecting railway safety, we learn from historical reports to build a connected network of hazards and accidents, forming a knowledge graph (KG), and apply it to railway hazard identification and risk assessment. First, the open source-British railway accident/incident reports are selected as the data source. The text augmentation algorithm in the text mining technology is introduced and optimized to achieve data enhancement. An ensemble model is constructed based on the hidden Markov model, conditional random field (CRF) algorithm, bidirectional long short-term memory (Bi-LSTM), and Bi-LSTM-CRF deep learning network, completing the named entity recognition of the reports. Then, using the random forest algorithm, the standardized classification of entities is accomplished, and the multi-dimensional knowledge graph network is established. Finally, after defining a series of safety-related feature parameters, the obtained KG is applied to the quantitative assessment of the corresponding risk level of the hazards. The results show that this approach realizes the visualization and quantitative description of the potential relationship among hazards, faults, and accidents by exploring the topological relationship of the railway accident network, further assisting the formulation of railway risk preventive measures.

Construction of 3D Model of College Public Physical Education Class Based on Text Mining Model

The responsibility and mission of higher education is to cultivate high-level talents needed for the development of society. The contemporary society has undergone great changes. The modern society characterized by the globalization of the knowledge economy has put forward social demands for higher education, and the development of science and technology with information and biotechnology as the core has put forward social demands on higher public physical education. Higher public physical education should creatively set new functions according to the development needs of the globalization of the knowledge economy and must cultivate people around the world, so that college courses can be adapted to the development needs of information technology, so as to meet the challenges of new technological revolutions. This research uses the literature research method, information research method, and observation method, uses text mining technology, and takes some ordinary colleges and universities as the survey objects. There are many problems in public physical teaching, and the corresponding feasible countermeasures and suggestions are put forward.

Research on Students' Satisfaction of Intelligent Learning Based on Text Mining Technology.

Recently, professionals have highlighted the need for students to have information technology and data analytic skills to be successful in the profession. To meet this demand, educators attempt to integrate technology into curricula. However, the satisfaction of students is of greater importance to evaluating curriculum quality than teaching. This study explores the perceptions that second-year undergraduate students (n = 51) enrolled in a Chinese University held about the teaching contents and teaching approaches of intelligent curriculum. Based on the data sample of the students' summary text for curriculum learning, this study adopts TFIDF analysis, topic modeling, text sentiment analysis, and other text mining technologies so as to have a profound analysis on the students' satisfaction. We find that: (1) the students have a higher satisfaction on the teaching contents involved in the financial sharing center compared to RPA financial robot; (2) students have a better adjustment to case analysis and flipped classroom compared to simulation training and classroom lecturing. Our findings and discussion should be of interest to leaders and teachers of business program seeking to integrate technology. We believe that this study's results provide opportunities to have a further improvement of the teaching contents and optimization of teaching design to effectively improve the curriculum quality in order to achieve enhancement of students' satisfaction.

Text data mining of power based on natural language processing technology

This paper first introduces the development of text mining technology, points out the difficulties of text mining technology, and then designs the power text mining based on natural language processing technology Then it introduces the typical application of text data mining technology in 95598 customer service complaints. Finally, it puts forward the application effect and challenge of power text mining.

Study on Influencing Factors of Construction Workers' Unsafe Behavior Based on Text Mining.

The unsafe behavior of construction workers is the key cause of safety accidents. The accident investigation report contains rich experience and lessons, which can be used to prevent and reduce the occurrence of safety accidents. In order to draw lessons from the accident and realize knowledge sharing and reuse, this paper uses text mining technology to analyze the data of 500 construction accident investigation reports in Shenzhen, China. Firstly, a Latent Dirichlet Allocation (LDA) topic model is used to identify the unsafe behavior of construction workers and its influencing factors. Then, with the help of Social Network Analysis, the importance of influencing factors and the relationship between them are identified. The results show that weak safety awareness, operating regulations, supervision dereliction of duty, equipment resources, and inadequate supervision of the construction party are the key and important factors. It is also found that there are correlations between weak safety awareness and supervision dereliction of duty, between equipment resources and poor construction environment, between organization and coordination and inadequate supervision of the construction party, and between operating regulations and hidden dangers investigation. This study not only helps to improve the theoretical system in the field of construction workers’ unsafe behavior but also helps managers to find the key control direction of construction safety, so as to effectively curb unsafe behavior of construction workers and improve the level of safety management.

Exploration of Topic Classification in the Tourism Field with Text Mining Technology—A Case Study of the Academic Journal Papers

This study collects abstracts of SSCI tourism journal papers between 2010 and 2019 from the WoS (Web of Science) database and uses a novel method of topic classification to explore the vocabulary characteristics of the classified articles. The corpora of abstracts are given quantitative Term Frequency–Inverse Document Frequency (TF–IDF) weights. A hierarchical K-means cluster analysis is then performed to automatically classify the articles; co-word analysis techniques are used to show the characteristics of feature words for distinct clusters, titles, and the consistency of the classified articles. Based on the results for 5783 abstracts, cluster analysis classifies the number of K-means clusters into six categories: travel, culture, sustainability, model, behavior, and hotel. A cross-check method is applied to assess the consistency of the topic classifications, list titles and keywords of the documents with the three smallest distances in each category and apply a strategic diagram to present the features of the distinct categories.

Quantitative Evaluation of Waste Separation Management Policies in the Yangtze River Delta Based on the PMC Index Model.

Numerous policies have been formulated and implemented to strengthen waste separation management activities in many countries. Waste separation management policies (WSMPs) must be evaluated as the precondition for reducing deviations from policy implementation and improving waste separation performance. Based on text mining technology and the construction of a policy modeling consistency (PMC) index model, we conducted a quantitative evaluation of 22 WSMPs issued by central governmental departments and provinces in the Yangtze River Delta, China from 2013 to 2021 and analyzed their optimization paths. The results suggest that the PMC index of the selected WSMPs has an upward trend. The average PMC index of 22 WSMPs was 6.906, indicating good quality in the policy texts. The PMC index identified seven, nine, five, and one of the policies as being perfect, excellent, good, and acceptable, respectively. The characteristics of WSMPs were further illustrated through PMC surface charts. Based on this, optimization paths for WSMPs with lower PMC indexes are proposed, which indicate that existing WSMPs have great potential for optimization in terms of harsher constraint regulations, context-appropriate incentives, and cultivation of market participants. Finally, this study provides a beneficial reference for similar cities or countries to improve their performance in the management of waste separation and environmental protection.

MetaboListem and TABoLiSTM: Two Deep Learning Algorithms for Metabolite Named Entity Recognition.

Reviewing the metabolomics literature is becoming increasingly difficult because of the rapid expansion of relevant journal literature. Text-mining technologies are therefore needed to facilitate more efficient literature reviews. Here we contribute a standardised corpus of full-text publications from metabolomics studies and describe the development of two metabolite named entity recognition (NER) methods. These methods are based on Bidirectional Long Short-Term Memory (BiLSTM) networks and each incorporate different transfer learning techniques (for tokenisation and word embedding). Our first model (MetaboListem) follows prior methodology using GloVe word embeddings. Our second model exploits BERT and BioBERT for embedding and is named TABoLiSTM (Transformer-Affixed BiLSTM). The methods are trained on a novel corpus annotated using rule-based methods, and evaluated on manually annotated metabolomics articles. MetaboListem (F1-score 0.890, precision 0.892, recall 0.888) and TABoLiSTM (BioBERT version: F1-score 0.909, precision 0.926, recall 0.893) have achieved state-of-the-art performance on metabolite NER. A training corpus with full-text sentences from >1000 full-text Open Access metabolomics publications with 105,335 annotated metabolites was created, as well as a manually annotated test corpus (19,138 annotations). This work demonstrates that deep learning algorithms are capable of identifying metabolite names accurately and efficiently in text. The proposed corpus and NER algorithms can be used for metabolomics text-mining tasks such as information retrieval, document classification and literature-based discovery and are available from the omicsNLP GitHub repository.

Multi-Level Analysis and Identification of Tumor Mutational Burden Genes across Cancer Types.

Tumor mutational burden (TMB) is considered a potential biomarker for predicting the response and effect of immune checkpoint inhibitors (ICIs). However, there are still inconsistent standards of gene panels using next-generation sequencing and poor correlation between the TMB genes, immune cell infiltrating, and prognosis. We applied text-mining technology to construct specific TMB-associated gene panels cross various cancer types. As a case exploration, Pearson’s correlation between TMB genes and immune cell infiltrating was further analyzed in colorectal cancer. We then performed LASSO Cox regression to construct a prognosis predictive model and calculated the risk score of each sample for receiver operating characteristic (ROC) analysis. The results showed that the assessment of TMB gene panels performed well with fewer than 500 genes, highly mutated genes, and the inclusion of synonymous mutations and immune regulatory and drug-target genes. Moreover, the analysis of TMB differentially expressed genes (DEGs) suggested that JAKMIP1 was strongly correlated with the gene expression level of CD8+ T cell markers in colorectal cancer. Additionally, the prognosis predictive model based on 19 TMB DEGs reached AUCs of 0.836, 0.818, and 0.787 in 1-, 3-, and 5-year OS models, respectively (C-index: 0.810). In summary, the gene panel performed well and TMB DEGs showed great potential value in immune cell infiltration and in predicting survival.

An Internet Articles Retrieval Agent Combined With Dynamic Associative Concept Maps to Implement Online Learning in an Artificial Intelligence Course

Online learning has been widely discussed in education research, and open educational resources have become an increasingly popular way to help learners acquire knowledge. However, these resources contain massive amounts of information, making it difficult for learners to identify Web articles that refer to computer science knowledge. This study developed an Internet articles retrieval agent combined with dynamic associative concept maps (DACMs). The system used text mining technology to analyze keywords to filter computer science articles. In previous research, concept maps were manually constructed; in this study, such maps can be automatically and dynamically generated in real time. In a case study of a fundamental course of artificial intelligence, this study designed two experiments to compare students’ learning behaviors while using this system and the Google search engine. The results of the first experiment showed that the experimental group searched for more knowledge articles on computer science using this agent, compared to the control group using the Google search engine. The learning performance of the experimental group was significantly better than that of the control group, while the cognitive load of the experimental group was significantly lower than that of the control group. Furthermore, the results of the second experiment showed that the learning progress of students using the agent was significantly greater than that of students who used the Google search engine. This illustrates that the agent effectively filtered computer science articles, and DACMs helped students gain a deeper understanding of academic concepts and knowledge related to artificial intelligence.

Sentiment Analysis of English Text with Multilevel Features

In natural language processing, text sentiment analysis is one of the important branches. It refers to the use of text mining and other technologies to extract attitudes, opinions, and other information from texts containing emotional information for analysis. Traditional sentiment analysis methods can be roughly divided into two categories: one is dictionary-based methods, and the other is machine learning-based methods. The former relies on the quality of the sentiment dictionary, while the latter relies on a large amount of high-quality data, so both have certain limitations. In text sentiment analysis research, word-level and sentence-level sentiment information extraction is a basic research task and has important research value. Through research, it is found that domain knowledge and context are two important factors influencing the extraction of emotional information. To this end, this paper proposes a text sentiment analysis method that integrates multiple features and constructs three features, which are based on the sentiment value feature of the dictionary, the expression feature, and the improved semantic feature, which are combined to build a text sentiment classification model. Aiming at the colloquial, irregular, and diverse features of English social media texts, this paper proposes a multilevel feature representation method. The sentiment classification experiments on English text show that the multilevel features proposed in this paper can effectively improve the F1_macro and accuracy of multiple model classifications. Compared with the existing research, the model in this paper improves the effect the most obvious.

A Bisociated Research Paper Recommendation Model using BiSOLinkers

In the current days of information overload, it is nearly impossible to obtain a form of relevant knowledge from massive information repositories without using information retrieval and filtering tools. The academic field daily receives lots of research articles, thus making it virtually impossible for researchers to trace and retrieve important articles for their research work. Unfortunately, the tools used to search, retrieve and recommend relevant research papers suggest similar articles based on the user profile characteristic, resulting in the overspecialization problem whereby recommendations are boring, similar, and uninteresting. We attempt to address this problem by recommending research papers from domains considered unrelated and unconnected. This is achieved through identifying bridging concepts that can bridge these two unrelated domains through their outlying concepts – BiSOLinkers. We modeled a bisociation framework using graph theory and text mining technologies. Machine learning algorithms were utilized to identify outliers within the dataset, and the accuracy achieved by most algorithms was between 96.30% and 99.49%, suggesting that the classifiers accurately classified and identified the outliers. We additionally utilized the Latent Dirichlet Allocation (LDA) algorithm to identify the topics bridging the two unrelated domains at their point of intersection. BisoNets were finally generated, conceptually demonstrating how the two unrelated domains were linked, necessitating cross-domain recommendations. Hence, it is established that recommender systems' overspecialization can be addressed by combining bisociation, topic modeling, and text mining approaches.

A comprehensive review on Arabic word sense disambiguation for natural language processing applications

AbstractIn communication, textual data are a vital attribute. In all languages, ambiguous or polysemous words' meaning changes depending on the context in which they are used. The ability to determine the ambiguous word's correct meaning is a Know‐distill challenging task in natural language processing (NLP). Word sense disambiguation (WSD) is an NLP process to analyze and determine the correct meaning of polysemous words in a text. WSD is a computational linguistics task that automatically identifies the polysemous word's set of senses. Based on the context some word comes into view, WSD recognizes and tags the word to its correct priori known meaning. Semitic languages like Arabic have even more significant challenges than other languages since Arabic lacks diacritics, standardization, and a massive shortage of available resources. Recently, many approaches and techniques have been suggested to solve word ambiguity dilemmas in many different ways and several languages. In this review paper, an extensive survey of research works is presented, seeking to solve Arabic word sense disambiguation with the existing AWSD datasets.This article is categorized under: Algorithmic Development > Text Mining Technologies > Machine Learning

Volatility forecasting for crude oil based on text information and deep learning PSO‐LSTM model

AbstractIn this paper, a method to forecast the volatility of crude oil market based on text mining technology and deep learning model is proposed. First, the text mining technology is used to construct the textual features hidden in the news headlines of crude oil market, including the emotional polarity score, investor sentiment classification, and risk factors. Then the textual features with other features reflecting fluctuations of the crude oil market are combined as inputs of the deep learning long short‐term memory (LSTM) model for better forecasting results. Furthermore, the particle swarm optimization (PSO) is used to optimize the hyper‐parameters of the deep learning LSTM model to further improve the forecasting ability. The results in this study show that the LSTM model optimized by PSO algorithm has reduced 7.66%, 8.15%, 8.2%, 10.93%, and 23.46% on the mean absolute error (MAE) of crude oil volatility forecasting compared with other models. And it is more stable in multiple‐step forecasting results compared with the econometric model. In addition, compared with the PSO‐LSTM model without textual features, the forecasting accuracy of the PSO‐LSTM model with textual features has reduced by 6.77% and 5.12% in the MAE and the mean square error (MSE), respectively.

An Empirical Study on the Precise Employment Situation-Oriented Analysis of Digital-Driven Talents with Big Data Analysis

This paper conducts an in-depth research analysis on the precise employment of college graduates in the context of big data using a number-driven approach. The textual information of the study is obtained by using in-depth interviews, and the evaluation index system of college students’ employment quality is constructed by combining the step-by-step coding method with rooting theory. The research on the current situation of employment recommendation platform research and the application status of big data in the employment recommendation platform is explored by using a bibliometric approach. And the innovative use of web crawler technology is used to comprehensively understand the recommendation function and status quo of the same type of recommendation platform, which provides a reference for the research of this platform. Based on the preliminary analysis of platform requirements and overall design, the overall design and functional implementation of the big data employment recommendation platform are carried out by using big data crawler technology, big data architecture technology, text mining technology, database technology, etc. The construction of a recommendation module based on user history information, a recommendation based on real-time user online behavior data, and hybrid recommendation carried out on the recommendation module to grasp all-round the platform is built based on a stakeholder perspective. Based on the platform construction, the initial platform operation and maintenance management mechanism was established from the stakeholder’s perspective. The Pearson correlation coefficient is used to objectively evaluate the current situation of talent supply in universities and talent demand in enterprises from the perspective of image and data. In the research on the development status of the big data education industry, the Lorenz curve and Gini coefficient are used to match the status of new big data majors with their college construction volume in each province and provide data support for the reasonable adjustment of majors setting in each province according to the education level.