Automatic Keyword Extraction Research Articles

Enhancing Keyword Extraction from Academic Articles Using Highlights

ABSTRACTKeywords facilitate rapid comprehension of academic papers for scholars, enhancing research efficiency. As some papers lack author‐assigned keywords, automated keyword extraction becomes crucial. Addressing the limited utilization of external paper information beyond titles and abstracts in prior studies, this research proposed leveraging the highlights section, which summarizes contributions and novelties, for unsupervised keyword extraction. We demonstrated performance improvements across three unsupervised keyword extraction models by integrating highlight information into abstracts. Further analysis indicates we can filter out irrelevant abstract sentences based on their semantic similarity to the highlights. Overall, this study pioneers the exploration of utilizing paper highlights for keyword extraction, simultaneously boosting unsupervised keyword extraction performance and providing insights for other abstract‐based text mining applications.

BRYT: Automated keyword extraction for open datasets

In today’s information-driven world, open data is crucial in making valuable structured data freely accessible to the public. However, the absence of quality metadata often hinders the findability and representation of this data. In this study we specifically focus on keywords, proposing a strategy for their automatic generation. In particular, we employed five existing keyword extraction methodologies (BERT, RAKE, YAKE, TEXTRANK, and ChatGPT) and proposed a novel hybrid methodology, named BRYT (read as bright). Our evaluation of these algorithms was conducted using Gestalt String Matching and Jaccard Similarity techniques. We validated our study using a selection of datasets from the EU data portal, specifically choosing those that exhibited potentially high-quality metadata. This included datasets that contained a substantial number of keywords and had comprehensive, relevant metadata. The results showed that 69.1% of the dataset keywords majorly matched (more than 50% or 5 keywords), 24.7% minorly matched (up to 50% or 5 keywords), and 6.2% did not match. The proposed hybrid model, BRYT, outperformed other algorithms in the major matches, while ChatGPT was a close second. YAKE outperformed the others in minor matches, and ChatGPT was again a close second. The evaluations concluded that BRYT consistently extracted more representative keywords in major matches, highlighting its effectiveness in improving findability. This study sets up a favorable field for further representative metadata extraction and population, making the data more findable, discoverable, and accessible.

An Ensemble Keyword Extraction Model for News Texts with Statistical and Graphical Features

Keyword extraction is an essential tool for many text mining applications such as automatic indexing, summarizing, classification, clustering and automatic filtering. Automated keyword extraction is essential as the daily text data to be reached and processed have increased tremendously over the Internet, e.g. millions of news articles are published daily online. In this paper, a novel ensemble model for automatic extraction of keywords from news articles is proposed. The proposed model handles keyword extraction as a sequence labeling task. Two sub-modules representing the statistical and graphical features by their calculated scores for each input token were combined in the token classification module. The Ensemble Token Classification module was trained and tested separately with the ensemble algorithms Random Forest, XgBoost, Decision Tree and Voting Classification. For training, we collected two news datasets from Kazakh and Russian news sites published in Cyrillic alphabet. We also collected an Arabic news dataset, ArabianNews. The performance of the model was also compared with the widely used 500N-KPCrowd dataset in the literature, which consists of English news content in Latin alphabet. The proposed model achieved the best performance with an [Formula: see text]-score of 0.71 and 0.86 on the 500N-KPCrowd and Russian datasets, respectively. We attained the best [Formula: see text]-score (0.97) with the KazakhNews and ArabianNews datasets.

A novel fuzzy logic-based approach for textual documents indexing

In the evolving landscape of information retrieval and natural language processing, the quest for more effective automatic keyword extraction (AKE) techniques from textual documents has become a pivotal research focus. Existing methodologies, while offering valuable insights, often grapple with the challenges posed by the imprecision and variability inherent in human language. This has led to a growing recognition of the need for innovative approaches to navigating textual content’s nuances more adeptly. In response to this imperative, this paper proposes a novel fuzzy indexing approach designed specifically for the indexing of textual documents. Fuzzy indexing, grounded in the principles of fuzzy logic, provides solutions for handling the inherent uncertainty and imprecision in natural language, especially when confronted with the intricacies of linguistic ambiguity and variability. By leveraging the power of fuzzy logic, we aim to enhance the precision of keyword extraction. This paper unfolds the intricacies of our fuzzy indexing approach, detailing the theoretical methodology through empirical evaluation and comparative analysis; we seek to demonstrate the efficacy of our approach in outperforming traditional methods in the context of fuzzy indexing for textual documents.

Research on the TF–IDF algorithm combined with semantics for automatic extraction of keywords from network news texts

Research on the TF–IDF algorithm combined with semantics for automatic extraction of keywords from network news texts

Combining sentiment analysis and text mining with content analysis of farm vet interviews on mental wellbeing in livestock practice.

The aim of the How Farm Vets Cope project was to co-design, with farm veterinary surgeons, a set of web-based resources to help them and others deal with the different situations that they can face. As part of the wider project, participants were recruited for one-to-one semi-structured phone interviews. These interviews focused on elements of job satisfaction and how the participants coped during periods of poor mental wellbeing or with setbacks and failure. Transcripts of these interviews were analysed using both quantitative methods of sentiment analysis and text mining, including term frequency/inverse document frequency and rapid automated keyword extraction, and qualitative content analysis. The twin aims of the analysis were identifying the important themes discussed by the participants and comparing the results of the two methods to see what differences, if any, arose. Analysis using the afinn and nrc sentiment lexicons identified emotional themes of anticipation and trust. Rapid automated keyword extraction highlighted issues around age of vets and support, whilst using term frequency/inverse document frequency allowed for individual themes, such as religion, not present across all responses, to be identified. Content analysis supported these findings, pinpointing examples of trust around relationships with farmers and more experienced vets, along with some examples of the difference good support networks can make, particularly to younger vets. This work has confirmed previous results in identifying the themes of trust, communication and support to be integral to the experience of practicing farm veterinary surgeons. Younger or less experienced vets recognised themselves as benefiting from further support and signposting, leading to a discussion around the preparation of veterinary students for entry into a farm animal vet practice. The two different approaches taken showed very good agreement in their results. The quantitative approaches can be scaled to allow a larger number of interviews to be utilised in studies whilst still allowing the important qualitative results to be identified.

Crash Contributing Factors and Patterns Associated with Fatal Truck-Involved Crashes in Bangladesh: Findings from the Text Mining Approach

Despite extensive research on traffic injury severities, relatively little is known about the factors contributing to truck-involved crashes in developing countries, especially in the context of Bangladesh. Because of the unavailability of authentic crash data sources, this study collected data from alternative sources such as online English news media reports. The current study prepared a database of 144 truck-involved fatal crash reports during the period of 12 months (January 2021 to December 2021). The crash reports contain a bag of 15,300 words. Several state-of-the-art text mining tools were utilized to identify crash patterns, including word cloud analysis, word frequency analysis, word co-occurrence network analysis, rapid automatic keyword extraction, and topic modeling. The analysis revealed several important crash contributing factors, such as the type of vehicle involved (auto-rickshaw, bus, van, motorcycle), the manner of collision (head-on), the time of the day (morning, night), driver behavior (speeding, overtaking, wrong-way driving), and environmental factors (dense fog). In addition, “coming from opposite direction” and “head-on collision” are two important sequences of events in truck-involved crashes. Truck drivers are also involved in crashes with trains at rail crossings. The findings of this research can assist policymakers in identifying crash avoidance strategies to lower truck-related crashes in Bangladesh.

Development system for coordination of activities of experts in the formation of machineschetable standards in the field of military and space activities based on ontological engineering: a case study

Standardization and technical regulation involve the digitization of international and regional standards into "smart" standards, introducing new requirements for the presentation of complex industrial manuals. The introduction of artificial intelligence and machine learning into the process of standardization, improving process automation, data analysis will provide an opportunity to create innovative standards. Creation of machine-readable standards and their presentation in the form of a database will contribute to better interoperability between systems. The article demonstrates the method of ontological engineering for the automation of partial methodological examination of documents in accordance with the National Standardization Plan. As part of the experiment, an independent tool was developed, based on the extraction of qualitative data, using an uncontrolled automatic keyword extraction algorithm. The algorithm does not require the creation of a learning corpus, can be applied to any text and language, and does not have limitations on the amount of processed data. The algorithm provides adjustment of the parameters of the repetition of keywords, with the possibility of taking into account less important keywords. The work presents the following components: model classification standards, essence extraction module, categorization, thesaurus formation, monitoring and analysis. Calculations were carried out using formalization, determination of the target function, establishment of similarity measures, and description of document features. The work presents the theoretical aspect of application, design and description of the functional system.

An Artificial Intelligence based automated case-based reasoning (CBR) system for severity investigation and root-cause analysis of road accidents – Comparative analysis with the predictions of ChatGPT

Road accidents have been progressively causing havoc in our society and certain preventive measures must be taken to reduce or possibly eliminate road accidents. The derivative of a road accident ranges from a mild injury to casualty. This research work mainly focusses on developing a novel case-based reasoning system to investigate and troubleshoot the cause of road accidents on a war-foot basis. First, the dominant attributes contributing to the cause of road accidents are identified and finalized as 28. A unique road accident dataset is developed which comprises of 1028 data collected from web resources, popular news magazines and extended further to large scale database of one-million cases by biased random number simulation. Each attribute is given a severity weightage of 1,2 and 3 for computing the net weighted score for a case in the database. Also, non-weighted scores are computed by introduction of a primary number dataset to maintain the uniqueness of the score which is further used for similarity analytics. Now, an accident news is randomly selected, and Rapid automatic keyword extraction (RAKE) schema is used as Natural language processor (NLP) for extracting the dominant keywords from the news articles. The extracted keywords are compared and further mapped into a factor-matrix comprising 28 attributes causing road accidents. Further, similarity analytics is performed to evaluate the severity scores and comparison of new cases. The system demonstrated high retrieval accuracy with all road accident cases collected from real world scenarios. This research has great prospects on troubleshooting road accident cases effectively and provides instant promising troubleshooting measures to prevent such accidents in the future. Also, the proposed framework might be useful for intelligent decision-making systems and automated driving systems. Based on the final outlook, a comprehensive framework for national road safety could be developed and passed as a valid law for implementation. Finally, the forecasted results of the proposed algorithm are compared with the predictions of Chat GPT program.

SkyWords: An automatic keyword extraction system based on the skyline operator and semantic similarity

This study presents a hybrid keyword extraction method called SkyWords. It implements a novel supervised step based on the skyline operator and the majority voting principle for high-quality candidate keyword selection and an unsupervised step based on contextual semantics for the candidate keyword ranking. To achieve this, firstly, we build a feature vector database using the features of known keywords and then apply the skyline operator to retrieve the dominating feature vectors. To select the candidate keywords of a document, we compare each word of the document against the dominating feature vectors and assume the words that are as good as the majority of the dominating feature vectors as candidate keywords. To obtain the final set of keywords, we rank the candidate keywords based on their semantic similarity to the document based on their vector representation using the MPNet sentence transformer. We conducted experiments on six benchmark scholarly datasets to evaluate the performance of SkyWords and compared the results against eleven baseline keyword extraction systems. The experimental results show that the proposed novel keyword selection algorithm reduced the number of candidate keywords by several folds. Moreover, SkyWords achieved statistically significant improvements over the baseline methods in precision, recall, and F1 score. Compared to the baseline regarding ranking-based metrics, SkyWords achieved the highest mean average precision score for all datasets and the highest mean reciprocal rank score for all datasets but one. Furthermore, SkyWords extracted more relevant keywords than the baseline methods.

Automatic Keyword Extraction Algorithm for Chinese Text based on Word Clustering

There are some problems in automatic keyword extraction of Chinese text, such as large feature extraction error, low precision of extracted keywords, and poor real-time performance. Therefore, an automatic keyword extraction algorithm for Chinese text based on word clustering is designed. Calculate keyword frequency, document frequency and inverse document frequency features through statistical algorithm, measure the degree of interdependence between keywords with the help of point mutual information, and construct keyword feature item quantification matrix with the help of vector space model corresponding to keywords and feature items to complete keyword feature quantification and realize keyword feature extraction of Chinese text. Calculate the average semantic similarity of keyword words, determine the similarity of keyword features, and eliminate the keyword features with high similarity; Set the comprehensive feature value of the importance of single word words in Chinese text, determine the importance of single word words in the text, remove the single word words with low importance, and use Bayesian framework to reduce the dimension of high-dimensional keyword feature data to realize preprocessing research. The mapping results of keyword vector space model are determined by word clustering algorithm, the text clusters of keyword space clustering results are calculated by clustering algorithm, and the keywords are classified by DBN method. On this basis, the automatic keyword extraction model of Chinese text is designed to realize the automatic keyword extraction of Chinese text. The experimental results show that the design algorithm can effectively reduce the feature extraction error and improve the extraction efficiency.

Automatic extraction of significant terms from the title and abstract of scientific papers using the machine learning algorithm: A multiple module approach

Keyword extraction is the task of identifying important terms or phrase that are most representative of the sourcedocument. Although the process of automatic extraction of keywords from title is an old method, it was mainly forextraction from a single web document. Our approach differs from previous research works on keyword extraction in severalaspects. For those who are non-expert of the scientific fields, understating scientific research trends is difficult. The purposeof this study is to develop an automatic method of obtaining overviews of a scientific field for non-experts by capturingresearch trends. This empirical study excavates significant term extraction using Natural Language Processing (NLP) tools.More than 15000 titles saved in a .csv file was our dataset and scripts written in Python were our process to compare how farsignificant terms of scientific title corpus are similar or different to the terms available in the abstract of that same scientificarticle corpus. A light-weight unsupervised title extractor, Yet Another Keyword Extractor (YAKE) was used to extract theresults. Based on our analysis, it can be concluded that these algorithms can be used for other fields too by the non-expertsof that subject field to perform automatic extraction of significant words and understanding trends. Our algorithm could be asolution to reduce the labour-intensive manual indexing process.

Performance Evaluation of Keyword Extraction Techniques and Stop Word Lists on Speech-To-Text Corpus

The dawn of conversational user interfaces, through which humans communicate with computers through voice audio, has been reached. Therefore, Natural Language Processing (NLP) techniques are required to focus not only on text but also on audio speeches. Keyword Extraction is a technique to extract key phrases out of a document which can provide summaries of the document and be used in text classification. Existing keyword extraction techniques have commonly been used on only text/typed datasets. With the advent of text data from speech recognition engines which are less accurate than typed texts, the suitability of keyword extraction is questionable. This paper evaluates the suitability of conventional keyword extraction methods on a speech-to-text corpus. A new audio dataset for keyword extraction is collected using the World Wide Web (WWW) corpus. The performances of Rapid Automatic Keyword Extraction (RAKE) and TextRank are evaluated with different Stoplists on both the originally typed corpus and the corresponding Speech-To-Text (STT) corpus from the audio. Metrics of precision, recall, and F1 score was considered for the evaluation. From the obtained results, TextRank with the FOX Stoplist showed the highest performance on both the text and audio corpus, with F1 scores of 16.59% and 14.22%, respectively. Despite lagging behind text corpus, the recorded F1 score of the TextRank technique with audio corpus is significant enough for its adoption in audio conversation without much concern. However, the absence of punctuation during the STT affected the F1 score in all the techniques.

Framing of COVID-19 in Newspapers: A Perspective from the US-Mexico Border.

The degree to which the media report a health emergency affects the seriousness with which the people respond to combat the health crisis. Engagement from local newspapers in the US has received scant scrutiny, even though there is a sizable body of scholarship on the analysis of COVID-19 news. We fill this void by focusing on the Rio Grande Valley area of the US-Mexico border. To understand the differences, we compared such local news coverage with the coverage of a national news outlet. After collecting the relevant news articles, we used sentiment analysis, rapid automatic keyword extraction (RAKE), and co-occurrence network analysis to examine the main themes and sentiments of COVID-19 news articles. The RAKE identified that county-specific news or local regulations are more prevalent among the key terms in The Monitor which are absent in USA Today. The co-occurrence network shows the coverage of the disruption of sports season in USA Today which is not present in The Monitor. The sentiment analysis presents fear emotion is more dominant in USA Today, but trust emotion becomes more prevalent in The Monitor news coverage. These findings show us that, although the subject of the health emergency is the same, local and national newspapers describe it in different ways, and the sentiments they convey are also not the same.

Government plans in the 2016 and 2021 Peruvian presidential elections: A natural language processing analysis of the health chapters

Background: While clinical medicine has exploded, electronic health records for Natural Language Processing (NLP) analyses, public health, and health policy research have not yet adopted these algorithms. We aimed to dissect the health chapters of the government plans of the 2016 and 2021 Peruvian presidential elections, and to compare different NLP algorithms. Methods: From the government plans (18 in 2016; 19 in 2021) we extracted each sentence from the health chapters. We used five NLP algorithms to extract keywords and phrases from each plan: Term Frequency–Inverse Document Frequency (TF-IDF), Latent Dirichlet Allocation (LDA), TextRank, Keywords Bidirectional Encoder Representations from Transformers (KeyBERT), and Rapid Automatic Keywords Extraction (Rake). Results: In 2016 we analysed 630 sentences, whereas in 2021 there were 1,685 sentences. The TF-IDF algorithm showed that in 2016, 26 terms appeared with a frequency of 0.08 or greater, while in 2021 27 terms met this criterion. The LDA algorithm defined two groups. The first included terms related to things the population would receive (e.g., ’insurance’), while the second included terms about the health system (e.g., ’capacity’). In 2021, most of the government plans belonged to the second group. The TextRank analysis provided keywords showing that ’universal health coverage’ appeared frequently in 2016, while in 2021 keywords about the COVID-19 pandemic were often found. The KeyBERT algorithm provided keywords based on the context of the text. These keywords identified some underlying characteristics of the political party (e.g., political spectrum such as left-wing). The Rake algorithm delivered phrases, in which we found ’universal health coverage’ in 2016 and 2021. Conclusion: The NLP analysis could be used to inform on the underlying priorities in each government plan. NLP analysis could also be included in research of health policies and politics during general elections and provide informative summaries for the general population.

News Recommender System Based on User Log History Using Rapid Automatic Keyword Extraction

There are many ways to find information; one of them is reading online news. However, searching for news online becomes more difficult because we should visit multiple platforms to find information. Sometimes, the recommended news doesn't match the user's interests. In many prior works, news recommendations are based on trending. Thus, the recommended news may not necessarily match the user's interests. To overcome this, we built a web-based news recommender system to make it easier for users to find news. We use the Rapid Automatic Keyword Extraction (RAKE) method in the recommendation process because this method can recommend news based on user preferences by utilizing user history logs. RAKE converts the title and content of the news into vector representation using Count vectorizer and applies the Cosine Similarity function to compare similarities between news. The test results show that the average performance of our proposed system is 90.8%, this accuracy outperforms earlier systems in terms of performance by the purpose of the recommender system, i.e., diversity, novelty, and relevance.

PubMed Author-assigned Keyword Extraction (PubMedAKE) Benchmark.

With the ever-increasing abundance of biomedical articles, improving the accuracy of keyword search results becomes crucial for ensuring reproducible research. However, keyword extraction for biomedical articles is hard due to the existence of obscure keywords and the lack of a comprehensive benchmark. PubMedAKE is an author-assigned keyword extraction dataset that contains the title, abstract, and keywords of over 843,269 articles from the PubMed open access subset database. This dataset, publicly available on Zenodo, is the largest keyword extraction benchmark with sufficient samples to train neural networks. Experimental results using state-of-the-art baseline methods illustrate the need for developing automatic keyword extraction methods for biomedical literature.

Extracting keywords of educational texts using a novel mechanism based on linguistic approaches and evolutive graphs

Keyword extraction is an important topic applicable to a wide range of areas such as span detection, information classification, sentiment analysis, and so on. There are hundreds of algorithms which can extract keywords from text documents. Many of these algorithms also use the functionality of the keywords, which is important, especially if we need to limit to a specific area of knowledge. This research work focuses on extracting keywords from educational texts. In an educational context, the keywords are the most important parts of the lesson and may answer the professor’s questions. Classic keyword extraction algorithms have a very low success rate extracting keywords from educational texts, as the words extracted by these algorithms are very different from those selected by the teachers. Normally, the most important words from an educational point of view would not match with the most repeated words in that text. This research work attempts to improve automatic keyword extraction in educative texts, avoiding professors from having to do this tedious task. The possibility of detecting keywords automatically could be a starting point for the creation of applications capable of generating questions and exercises automatically. We tested whether the most popular word extraction algorithms were able to extract the keywords selected by professors efficiently. The result obtained by current algorithms were no good at all, as they showed a low true positive rate or very high rates of false positive. Due to these reasons, we designed a novel algorithm based on linguistic approaches and evolutive graphs. The research method to obtain the new algorithm was the design of a complex graph which operates with numerous characteristics related to the relationships between words and their linguistic properties. The graph was trained with a set of texts and keywords to establish the optimal weights for each of the characteristics. The proposal achieves a rate of true positives (TP) and F1 score significantly better than other algorithms.

Keyword Extraction from Kazakh News Dataset with BERT

Keywords provide a concise and precise description of the document's content. Due to the importance of the keyword and the difficulty of manual markup, automatic keyword extraction makes this process easy and fast. In this paper, Keyword Extraction from Kazakh News Dataset was presented. Model performance results were obtained by using the BERT base - uncased and BERT-base-multilingual-uncased pre-trained language model for the newly compiled Kazakh News Dataset-KND. Compiled Kazakh news data set consists of 7060 data. Data were collected from the web pages anatili.kazgazeta.kz, Bilimdinews.kz, and zhasalash.kz using the BeautifulSoap and Requests libraries. These web pages mostly contain news, history, and literary texts. The dataset includes the publication name or news title, the author of the publication or news subject, and the URL of the Kazakh news site. In the evaluation of the training results, it was observed that the BERT base-multilingual-uncased F-score performance was higher than the BERT model.

FacTeR-Check: Semi-automated fact-checking through semantic similarity and natural language inference

Our society produces and shares overwhelming amounts of information through Online Social Networks (OSNs). Within this environment, misinformation and disinformation have proliferated, becoming a public safety concern in most countries. Allowing the public and professionals to efficiently find reliable evidence about the factual veracity of a claim is a crucial step to mitigate this harmful spread. To this end, we propose FacTeR-Check, a multilingual architecture for semi-automated fact-checking and hoaxes propagation analysis that can be used to implement applications designed for both the general public and for fact-checking organisations. FacTeR-Check implements three different modules relying on the XLM-RoBERTa Transformer architecture to evaluate semantic similarity, to calculate natural language inference and to build search queries through automatic keywords extraction and Named-Entity Recognition. The three modules have been validated using state-of-the-art benchmark datasets, exhibiting good performance in all of them. Besides, FacTeR-Check is employed to collect and label a dataset, called NLI19-SP, composed of more than 40,000 tweets supporting or denying 60 hoaxes related to COVID-19, released publicly. Finally, an analysis of the data collected in this dataset is provided, which allows to obtain a deep insight of how disinformation operated during the COVID-19 pandemic in Spanish-speaking countries.