Term Frequency-inverse Document Frequency Algorithm Research Articles

Do you love traveling to the beach or mountain? Predicting personality traits and choice behaviour

ABSTRACT Several personality-predicting tools are being used by managers in their strategic decision-making process. The most common are the Big Five model and the Myers – Myers-Briggs Type Indicator model, respectively. This study deviates and tests a novel personality prediction model. Specifically, it utilizes the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm as a feature extraction method to map personality traits based on consumers’ textual data from the Kaggle MBTI Personality Type dataset. This study uses realistic data gathered from traveller reviews and comments on hotel stays from TripAdvisor’s widely recognised platform to predict different personality traits and their travel destination preferences, i.e. beach or mountain. The contribution of this study lies in the identification of multiple dimensions of peoples’ personality traits and their relationship with their preferences for travel locations. This proposed trait classification mechanism can assist marketing managers in effectively carrying out customer segmentation, setting realistic goals, and optimizing marketing strategies.

Automating the Extraction of Words and Topics in Indonesian Using the Term Frequency-Inverse Document Frequency Algorithm and Latent Dirichlet Allocation

Keyword extraction and topic modeling in the analysis of Gojek user reviews in Indonesian are very important. By understanding user preferences and needs through keyword extraction, as well as grouping user reviews into different topics through topic modeling, stakeholders can use the information to further improve services. This research uses TF-IDF and LDA approaches to analyze text data from Gojek user reviews and feedback. The data spans from Nov 5, 2021, to Jan 2, 2024, totaling 225,002 rows. Each row includes username, content, time, and app version. The focus is on content reviews. The average length is 8 words, with a maximum of 104 and a minimum of a few words. The variability indicates a non-normal distribution. Preprocessing is conducted to maintain topic analysis accuracy. The TF-IDF method is used to extract relevant keywords, while the LDA approach is used to model the topics in user reviews. The topic analysis reveals patterns in Gojek user reviews. The first topic discusses experience, services, and affordable pricing. The second emphasizes app usability and benefits. The third relates to promos, discounts, and vouchers. The fourth reflects positive evaluations of service quality. However, the fifth topic highlights high costs and app issues. The sixth underscores overall user satisfaction and service convenience. Testing on the topic model yielded a coherence level of 0.509, indicating that the model's topics demonstrate a good level of consistency in finding relevant topics from Gojek user review data. The use of a combination of TF-IDF and LDA in Indonesian text analysis, particularly in the context of Gojek user reviews, is an important step in enhancing understanding and utilization of text data to improve overall user experience.

An extended TF-IDF method for improving keyword extraction in traditional corpus-based research: An example of a climate change corpus

Keyword extraction involves the application of Natural Language Processing (NLP) algorithms or models developed in the realm of text mining. Keyword extraction is a common technique used to explore linguistic patterns in the corpus linguistic field, and Dunning’s Log-Likelihood Test (LLT) has long been integrated into corpus software as a statistic-based NLP model. While prior research has confirmed the widespread applicability of keyword extraction in corpus-based research, LLT has certain limitations that may impact the accuracy of keyword extraction in such research. This paper summarized the limitations of LLT, which include benchmark corpus interference, elimination of grammatical and generic words, consideration of sub-corpus relevance, flexibility in feature selection, and adaptability to different research goals. To address these limitations, this paper proposed an extended Term Frequency-Inverse Document Frequency (TF-IDF) method. To verify the applicability of the proposed method, 20 highly cited research articles on climate change from the Web of Science (WOS) database were used as the target corpus, and a comparison was conducted with the traditional method. The experimental results indicated that the proposed method could effectively overcome the limitations of the traditional method and demonstrated the feasibility and practicality of incorporating the TF-IDF algorithm into relevant corpus-based research.

AI Based Chatbot: A Case Study Afghanistan Healthcare Services Mental Health Disorder

Artificial intelligence increasingly integrates our daily lives with the creation and analysis of intelligent software and hardware, called intelligent agents. Intelligent agents can do a variety of tasks ranging from labor work to sophisticated operations. A Chatbot is a typical example of an artificial intelligence system. For developing artificial intelligence Chatbot, we have implemented encoder-decoder attention mechanism architecture memory cells, TFIDF (term frequency-inverse document frequency) algorithm and LLM (Large Language Module). To conduct this research, mixed methods research could involve combining both qualitative and quantitative methods to provide a more comprehensive understanding of the research topic. Survey utilized as the main methods for collecting the primary data and reviewed the existing literature for collecting the secondary data in this research. The data was collected from 18 participants, including medical doctors, patients, lecturers and university students in Afghanistan. Additionally, secondary data was obtained through a review of literature from other countries that have faced similar situations. Moreover, the analysis reveals a widespread belief among respondents that the implementation of AI based Chatbot for Afghanistan healthcare service in mental health disorder will contribute to reduce illness in Afghanistan.

Fingerprint Finder: Identifying Genomic Fingerprint Sites in Cotton Cohorts for Genetic Analysis and Breeding Advancement.

Genomic data in Gossypium provide numerous data resources for the cotton genomics community. However, to fill the gap between genomic analysis and breeding field work, detecting the featured genomic items of a subset cohort is essential for geneticists. We developed FPFinder v1.0 software to identify a subset of the cohort's fingerprint genomic sites. The FPFinder was developed based on the term frequency-inverse document frequency algorithm. With the short-read sequencing of an elite cotton pedigree, we identified 453 pedigree fingerprint genomic sites and found that these pedigree-featured sites had a role in cotton development. In addition, we applied FPFinder to evaluate the geographical bias of fiber-length-related genomic sites from a modern cotton cohort consisting of 410 accessions. Enriching elite sites in cultivars from the Yangtze River region resulted in the longer fiber length of Yangze River-sourced accessions. Apart from characterizing functional sites, we also identified 12,536 region-specific genomic sites. Combining the transcriptome data of multiple tissues and samples under various abiotic stresses, we found that several region-specific sites contributed to environmental adaptation. In this research, FPFinder revealed the role of the cotton pedigree fingerprint and region-specific sites in cotton development and environmental adaptation, respectively. The FPFinder can be applied broadly in other crops and contribute to genetic breeding in the future.

Optimizing production logistics through advanced machine learning techniques: A study on resource allocation for small-batch and multi-variety challenges

In light of increasing consumer purchasing power and the growing diversification of demands, the emergence of small-batch and multi-variety requirements has posed substantial challenges to production manufacturing, particularly in on-site production logistics management. This study aims to address the issues of effective material flow and resource allocation in production logistics management by investigating a method for the rapid and accurate allocation of supply logistics resources. Leveraging the extensive logistics resource allocation data available in the Plan For Every Part system, this research utilizes the Term Frequency-Inverse Document Frequency algorithm to filter out less discriminative data. Additionally, a recommender system based on machine learning, specifically the Recsys (Recommender System) employing similarity algorithms, is employed to construct a logistics resource allocation recommendation model. The effectiveness of this approach is validated through a case study that involves material resource allocation recommendations in a specific remote control production workshop. The validation results indicate that, compared to traditional logistics resource allocation processes, the proposed model optimizes resource allocation recommendations in production logistics, resulting in a significant improvement in material delivery punctuality and overall operational efficiency in enterprises.

Urban Complexity and the Dynamic Evolution of Urban Land Functions in Yiwu City: A Micro-Analysis with Multi-Source Big Data

The diversification of business forms leads to functional and spatial complexity in cities. The efficient determination of the complexity of an urban system is the basis for the scientific monitoring of the multi-functional aggregation within cities. Previous studies on the urban spatial structure were limited by the difficulty of collecting micro-data and the high time cost, and they focused on the macro-spatial structure, lacking fine-grained investigations of the micro-spatial structure. Additionally, high-resolution remote sensing images, which mainly rely on the textural characteristics of the spectrum of ground objects, cannot detect the social and economic functions of ground objects. Thus, it is difficult to meet the actual needs of urban planning and management. The purpose of this paper is to automatically identify the spatial heterogeneity and temporal variation of urban land use functions in the context of complex urban systems. The TF-IDF (term frequency–inverse document frequency) algorithm, a machine learning classification algorithm, and other methods are applied to identify the urban functions and distribution characteristics of the main urban area based on the POI (point of interest) data and urban form data. The results show the following: (1) From 2012 to 2022, all types of land use in Yiwu city grew at different rates, with logistics and warehousing space growing the fastest, which is in line with Yiwu’s goal of building a national logistics center for trade and services. (2) The residential area has a spatial structure with a dense central circle and a scattered periphery extending from northeast to southwest and from east to west. (3) The commercial service sector shows clear spatial differentiation between the core and the periphery. The commercial functional areas of Niansanli, Houzhai, and Chengxi, where the number of commercial POIs is relatively small, are located at the intersection of the administrative subdistricts near the city center, indicating that the commercial economic activities of the downtown subdistrict have a certain spillover effect on adjacent subdistricts. (4) The public facilities of each subdistrict are generally located in the core of each subdistrict, which ensures better convenience and accessibility. (5) Industrial land with a large total area that is scattered and mixed with urban residential land gradually tends to be centralized, forming an industrial belt around the city. This study comprehensively considers the aggregation relationship between urban buildings and land use and improves the accuracy of land identification and functional zoning.

Product ranking through fusing the wisdom of consumers extracted from online reviews on multiple platforms

Ranking products based on online reviews has become an important measure to support consumers’ purchasing decisions. How to make an effective decision considering online review information from different e-commerce platforms is a challenge. In this regard, this study introduces a large-scale group decision-making (LSGDM) method to assist users in making purchasing decisions by extracting the collective wisdom of reviewers across different platforms. First, we use the lexical analysis system, term frequency-inverse document frequency algorithm, and sentiment dictionary to process online review data and obtain product attributes, the weights of attributes, and sentiment scores of reviews, respectively. The weights of platforms are determined using an integrated method that considers the characteristics of each platform. Afterwards, we present an LSGDM method to achieve the coordination of the wisdom of reviewers. We collect online reviews of four mobile phones from Tmall, JD and Suning, providing experimental analyses to demonstrate the applicability of our proposed method.

Innovation technology opportunity identification of civil aircraft mechanical connections based on generative topographic mapping.

In order to advance civil aircraft manufacturing to higher levels, there is an urgent need to identify technological innovation opportunities to help new technology development. This paper first analyses the current state of the research field and determines the topic. It preprocesses papers and patents within the research topic to obtain a base database. Then, the database is analyzed using the LDA (Latent Dirichlet Analysis) cluster analysis method. The TF-IDF (Term Frequency-Inverse Document Frequency) algorithm processes the data to obtain critical technical words. The abstracts of patents and papers are processed to construct a binary-based vector of technical keywords. The papers and patents are visualized in a two-dimensional space technology map by generative topographic mapping (GTM) to create a technology map to identify technology blank dots. The combination of technologies characterized by each technology blank dot is obtained by GTM inverse mapping. Finally, technology opportunities with a high probability of development are identified to achieve innovation opportunity identification. It also provides countermeasures for the research institution, enterprise, sector, and industry. After research and analysis, the future in the mechanical connection technology of civil aircraft is necessary to strengthen basic technology development and improve the study of intelligence, integration, and flexibility. Technology such as sensors and lasers can improve the precision and efficiency of mechanical connections.

Deep Learning and Text Mining: Classifying and Extracting Key Information from Construction Accident Narratives

Construction accidents can lead to serious consequences. To reduce the occurrence of such accidents and strengthen the execution capabilities in on-site safety management, managers must analyze accident report texts in depth and extract valuable information from them. However, accident report texts are usually presented in unstructured or semi-structured forms; analyzing these texts manually requires a lot of time and effort, it is difficult to cope with the demand of analyzing a large number of accident texts, and the quality of key information extracted manually may be poor. Therefore, this study proposes a classification method based on natural language processing (NLP) technology. First, we developed a text classification model based on a convolutional neural network (CNN) that can automatically classify accident categories based on accident text features. Next, taking the classified fall accidents as an example, we extracted key information from accident narratives using the term frequency-inverse document frequency (TF-IDF) method and presented it visually using word clouds. The results show that the overall accuracy of the CNN model reaches 84%, which is better than the other three shallow machine-learning models. Then, eight key accident areas and three accident-prone operations were identified using the TF-IDF algorithm. This study can provide important guidance for project managers and can be used for on-site safety management to help prevent production safety accidents.

Tourism Destination Article Search Features using TF-IDF and Cosine similarity

In the current digital era, the increasing public interest in searching for information about travel destinations necessitates an effective and accurate search system. However, search results for travel destination articles often yield irrelevant or inadequate outcomes. To address this issue, this paper proposes applying the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm and Cosine Similarity in the search feature for travel destination articles. By employing these algorithms, the search system is anticipated to deliver more relevant and accurate results according to user needs.
 This research contributes to developing an effective search system for travel destination articles, assisting users in obtaining relevant and high-quality information about the destinations they are searching for. The methodology involves collecting data on travel destination articles, implementing the TF-IDF algorithm to evaluate term importance, and utilizing Cosine Similarity to measure the similarity between articles and user queries.
 The study results demonstrate that implementing the TF-IDF algorithm and Cosine Similarity in the search feature for travel destination articles enhances the accuracy and relevance of search results. Users can quickly discover articles that align with their queries, improving their search experience. In conclusion, this research highlights that applying the TF-IDF algorithm and Cosine Similarity in the search feature significantly improves the accuracy and relevance of search results for travel destination articles. This enhances the search experience for users seeking information about travel destinations.

A natural language processing based technique for sentiment analysis of college english corpus.

The college English corpus can help us better master English, but how to obtain the desired information from a large number of English corpus has become the focus of information technology. Based on the natural language processing (NLP) technology, a sentiment analysis model is built in this article. An improved term frequency-inverse document frequency (TF-IDF) algorithm is proposed in this article, where the weighted average method is used to determine the emotional value of each emotional word. The inspirational words are used to obtain the English corpus's emotional tendency and emotional value. The results show that the model has high classification accuracy and operation efficiency when selecting feature words. Compared with the TF-IDF, the improved TF-IDF algorithm added the necessary information weight processing and word density weight processing to two new processing links, which can significantly improve the efficiency of college English learning.

A Method of Extracting Malware Features Based on Gini Impurity Increment and Improved TF-IDF

In recent years, the quantities and types of malwares have grown explosively, which bring many challenges to identify and detect them. In order to improve the identification efficiency of malicious code, a malicious code feature representation method based on feature dimension reduction is proposed. By fusing the Gini impurity increment and the Improved Term Frequency-Inverse Document Frequency algorithm (ITF-IDF), ΔGini-Improving Term frequency inverse document frequency (ΔGini-ITFIDF) method is presented, which can get more valuable assembly instruction features for family detection. ΔGini-ITFIDF standardizes the assembly instructions of the PE disassembly files, then, measures the two indicators of the expected error rate increment and weight of the malicious code assembly instruction features, and obtains more valuable features to identify malicious codes. The experimental results show that the classification accuracy of the ITF-IDF algorithm is significantly improved compared with the ITF-IDF algorithm. At the same time, ΔGini-ITFIDF can effectively improve the classification performance.

Construction of Intelligent Recommendation Retrieval Model of FuJian Intangible Cultural Heritage Digital Archives Resources

In order to improve the consistency between the recommended retrieval results and user needs, improve the recommendation efficiency, and reduce the average absolute deviation of resource retrieval, a design method of intelligent recommendation retrieval model for Fujian intangible cultural heritage digital archive resources based on knowledge atlas is proposed. The TG-LDA (Tag-granularity LDA) model is proposed on the basis of the standard LDA (Linear Discriminant Analysis) model. The model is used to mine archive resource topics. The Pearson correlation coefficient is used to measure the relevance between topics. Based on the measurement results, the FastText deep learning model is used to achieve archive resource classification. According to the classification results, TF-IDF (term frequency–inverse document frequency) algorithm is used to calculate the weight of resource retrieval keywords to achieve resource retrieval, and a recommendation model of intangible cultural heritage digital archives resources is built through the knowledge map to achieve comprehensive and personalized recommendation of resources. The experimental results show that the recommendation and retrieval results of the proposed method are more in line with users’ needs, can provide users with personalized digital archive resources, and the average absolute deviation of resource retrieval is low, the recommendation efficiency is high, and the utilization effect of archive resources is effectively improved.

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.

A Systematic Review of COVID-19 Geographical Research: Machine Learning and Bibliometric Approach

The rampant COVID-19 pandemic swept the globe rapidly in 2020, causing a tremendous impact on human health and the global economy. This pandemic has stimulated an explosive increase of related studies in various disciplines, including geography, which has contributed to pandemic mitigation with a unique spatiotemporal perspective. Reviewing relevant research has implications for understanding the contribution of geography to COVID-19 research. The sheer volume of publications, however, makes the review work more challenging. Here we use the support vector machine and term frequency-inverse document frequency algorithm to identify geographical studies and bibliometrics to discover primary research themes, accelerating the systematic review of COVID-19 geographical research. We confirmed 1,171 geographical papers about COVID-19 published from 1 January 2020 to 31 December 2021, of which a large proportion are in the areas of geographic information systems (GIS) and human geography. We identified four main research themes—the spread of the pandemic, social management, public behavior, and impacts of the pandemic—embodying the contribution of geography. Our findings show the feasibility of machine learning methods in reviewing large-scale literature and highlight the value of geography in the fight against COVID-19. This review could provide references for decision makers to formulate policies combined with spatial thinking and for scholars to find future research directions in which they can strengthen collaboration with geographers.

Extractive Text and Video Summarization using TF-IDF Algorithm

Abstract: Text summarization is a technique for extracting concise summaries from a large text without sacrificing any important information. It's a good way to extract crucial information from documents. The rapid rise of the internet has resulted in a substantial surge in data all across the world. It has become difficult for humans to manually summarise big documents. Automatic Text Summarization is an NLP technique that lowers the time and efforts required by a human to create a summary. Text summarising techniques are divided into two categories: extractive and abstractive. In the extractive approach, text summarising techniques choose sentences from documents based on a set of criteria. In the abstractive approach, text summarising techniques strive to improve sentence coherence by reducing redundancies and explaining the context of sentences. The extractive summarization approach is the subject of this paper. There are several methods for summarising data, including TF-IDF, Text Rank, PageRank, and Latent Dirichlet Allocation (LDA). This work examines Text Summarization using the TFIDF Algorithm, a numerical measure that ranks the value of a word in a document based on how frequently it appears in that document and a set of documents. The application of the TF-IDF Algorithm for text, document, article, and video summarization is described in this study. There are no repetitions in the results, and for some searches, they are nearly identical to the summary results provided by humans. This algorithm offers a sentence extraction technique that selects the most diverse top-ranked sentences. Keywords: Extractive Summarization, Term Frequency-Inverse Document Frequency (TF-IDF), Natural Language Processing (NLP), Text Summarization, Video Summarization

CLUSTERING BERITA MENGGUNAKAN ALGORITMA TF-IDF DAN K-MEANS DENGAN MEMANFAATKAN SUMBER DATA CRAWLING PADA SITUS DETIK.COM

News clustering aims to identify each news group that is formed from the implementation of the K-Means method which is based on the word weighting process using the TF-IDF (Term Frequency Inverse Document Frequency) Algorithm. The clustering process uses news crawled from the detik.com site for a period of one year (2018), totaling 124,509 news stories and stored in the form of a CSV (Comma Seperated Value) file. Before carrying out the clustering process, the previous dataset must go through a text-processing stage in the form of: case folding, tokenizing, stopword removal, and stemming. The TF-IDF and K-Means methods are used for the clustering process. The TF-IDF method assigns weights to each keyword in each category to find the similarity of keywords to the available categories, then continues with the K-Means Method for the grouping process based on similar characteristics / similarities between documents. In the process, there are two implementations of the K-Means method, each using 16 centroids and 12 centroids. This is because in the first process, there are groups / clusters that cannot be identified because they contain common words, so a second implementation is needed. Based on the results of testing on 124,509 news stories, there are 27 news groups that have been successfully identified with adequate application capabilities in processing large data.

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, 22 terms appeared with a frequency of 0.05 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.

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, 22 terms appeared with a frequency of 0.05 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.