RAKE Algorithm Research Articles

Suicidal Ideation Detection and Influential Keyword Extraction from Twitter using Deep Learning (SID)

INTRODUCTION: This paper focuses on building a text analytics-based solution to help the suicide prevention communities to detect suicidal signals from text data collected from online platform and take action to prevent the tragedy. OBJECTIVES: The objective of the paper is to build a suicide ideation detection (SID) model that can classify text as suicidal or non-suicidal and a keyword extractor to extracted influential keywords that are possible suicide risk factors from the suicidal text. METHODS: This paper proposed an attention-based Bi-LSTM model. An attention layer can assist the deep learning model to capture influential keywords of the model classifying decisions and hence reflects the important keywords from text which highly related to suicide risk factors or reason of suicide ideation that can be extracted from text. RESULTS: Bi-LSTM with Word2Vec embedding have the highest F1-score of 0.95. Yet, attention-based Bi-LSTM with word2vec embedding that has 0.94 F1-score can produce better accuracy when dealing with new and unseen data as it has a good fit learning curve. CONCLUSION: The absence of a systematic approach to validate and examine the keyword extracted by the attention mechanism and RAKE algorithm is a gap that needed to be resolved. The future work of this paper can focus on both systematic and standard approach for validating the accuracy of the keywords.

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.

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.

And the Rest is History: Measuring the Scope and Recall of Wikipedia’s Coverage of Three Women’s Movement Subgroups

Narrating history is perpetually contested, shaping and reshaping how nations and people understand both their pasts and the current moment. Measuring and evaluating the scope of histories is methodologically challenging. In this paper we provide a general approach and a specific method to measure historical recall. Operationalizing historical information as one or more word phrases, we use the phrase-mining RAKE algorithm on a collection of primary historical documents to extract first-person historical evidence, and then measure recall via phrases present on contemporary Wikipedia, taken to represent a publicly-accessible summary of existing knowledge on virtually any historical topic. We demonstrate this method using women's movements in the United States as a case study of a debated historical field. We found that issues important to working-class elements of the movement were less likely to be covered on Wikipedia compared to other subsections of the movement. Combining this method with a qualitative analysis of select articles, we identified a typology of mechanisms leading to historical omissions: paucity, restrictive paradigms, and categorical narrowness. Our approach, we conclude, can be used to both evaluate the recall of a body of history and to actively intervene in enlarging the scope of our histories and historical knowledge.

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, nine terms appeared with a frequency of 0.10 or greater, while in 2021 43 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, nine terms appeared with a frequency of 0.10 or greater, while in 2021 43 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.

An assortment of Query Based Summarization technique (QBS) – A Study

This paper presents latest techniques followed in Query based single and multi-document summarization. In this era, we see an exponential growth of text data in all fields, it is rigid to get vital and precise information on time. Automatic Text Summarization is obligatory to reduce the stint to analyses elongated and complicated document. Text summarization is categorized based on many factors, each has its own merits and demerits. Query based summarization has attracted increasing interest due to its usage in many applications. This survey includes query-based summarization using graph, hyper graph, RAKE algorithm and Linguistic knowledge. DUC is the popular data set used in most text summarization, but due to its inability to suit various kinds of queries, some authors have used their own data set.

Predicting Bug Priority Using Topic Modelling in Imbalanced Learning Environments

Manual classification of bug reports is time-consuming as the reports are received in large quantities. Alternatively, this project proposed automatic bug prediction models to classify the bug reports. The topics or the candidate keywords are mined from the developer description in bug reports using RAKE algorithm and converted into attributes. These attributes together with the target attribute—priority level—construct the training datasets. Naïve Bayes, logistic regression, and decision tree learner algorithms are trained, and the prediction quality was measured using area under recursive operative characteristics curves (AUC) as AUC does not consider the biasness in datasets. The logistics regression model outperforms the other two models providing the accuracy of 0.86 AUC whereas the naïve Bayes and the decision tree learner recorded 0.79 AUC and 0.81 AUC, respectively. The bugs can be classified without developer involvement and logistic regression is also a potential candidate as naïve Bayes for bug classification.

Automatic scoring method of English composition based on language depth perception

AutomatedEssaySystem (AES) refers to a system for evaluating and rating compositions by using techniques in the fields of statistics, natural language processing and linguistics. The selection of composition features is one of the key issues in the study of automatic composition scoring. This paper abstracts the features of language sense from the depth of language perception, which makes up for the shortcomings of the automatic scoring system of shallow features (such as vocabulary difficulty, grammar, etc.). The features of language sense are mainly the similarity of keywords extracted from the first and last paragraphs of a composition by rake algorithm, the similarity of texts calculated by cosine similarity to the context content of a composition and the similarity detection of composition language materials by automata. Finally, from the three aspects of correlation, error and overall accuracy, it analyzes whether the deep-seated language features improved the scoring ability of AES system. The experimental results show that the added depth perception features enhance the language ability of automatic scoring and are closer to manual scoring.

Investigating the Relevant Agro Food Keyword in Malaysian Online Newspapers

Online newspaper is a valuable resource of information for decision making. To extract relevant information from them is a challenging process when their volume is massive, and its knowledge is in an unstructured form that is scattered on every page. This situation becomes more complicated when different news providers have different styles of journalism when reporting a similar event and use different concepts and terms. In this study, we examined the three Malaysian English online newspapers in order to identify knowledge in terms of the most relevant keywords used in daily online news. The news articles related to Agro-food industries were taken from online news websites - The Star Online, The Sun Daily, and The News Straits Times. During the extraction, about 458 Agro-food industries news articles were scrapped from the website within the time frame of 2014-2017. The keywords were extracted using the RAKE algorithm and were classified into 4 groups i.e. agriculture, livestock, fishery and miscellaneous. The agriculture keywords group was found as the most frequent keywords in all newspapers (58%) and it was followed by the livestock (23%), fishery (12%), and miscellaneous (7%). Through the analysis, there were 146 Agro-related keywords found in all newspapers, repeated 720 times, and the highest Agro terms were found in The Star Online (35.13%), followed by The Sun Daily (33.78%), and The News Straits Times (31.08%). There were 12 Agro keywords0 which considered as the most relevant when they appear in all newspapers- palm oil, rice, fruits, fish, vegetable, livestock, paddy, crop, chicken, animal, meat, and beef. The ‘palm oil’ is the most popular keyword among the three newspapers and it was found 37 times (38.9%) in The Star Online, 26 times (37.9%) in News Straits Time, and repeated 22 times (23.2%) in the Sun. The identified keywords can be recommended as input to form a future Agro inventory.

The Development of IoT Compression Technique To Cloud

The main problem of data transmission is how to reduce the length of data packet delivery, so it can reduce the time of sending data. One method that can be used to reduce the data size is by compressing the data size. Data compression is a technique for compressing data to get the data with smaller size than the original size so that it can shorten the data exchange timeThis study aims to develop the data compression techniques by modifying and combining the coding and modelling techniques based on the RAKE algorithm. This study testing experiments use 4 different methods in 5 different time-periods to determine the value of the compression, decompression efficiency parameters, and the data transmission time parameters.The result of this study is the data coding technique that using decimal to binary converter data and the modeling technique by calculating the residue from the sensor value will produce data in small sizes and get a compression efficiency value of 45%. For coding techniques using ASCII and modeling techniques with XOR operations will produce bigger size data and the compression efficiency value of 71%. In testing data decompression, the decompression efficiency value of 100%, there is no data loss.

Efficiently Identification of Misrepresentation in Social Media Based on Rake Algorithm

The social organizations offer an extensive variety of extra data to advance standard learning calculations; the most difficult part is separating the applicable data from arranged information. Fake conduct is indistinctly disguised both in nearby and social information, making it considerably harder to define valuable contribution for expectation models. Beginning from master learning, this paper prevails to efficiently join interpersonal organization impacts to identify misrepresentation for the Belgian legislative standardized savings foundation, and to enhance the execution of conventional non-social extortion expectation undertakings. Finding the semantic reasonable subjects from the colossal measure of rational points from the substantial measure of User Generated Content (UGC) in online networking would encourage numerous downstream uses of shrewd processing. Subject models, as a standout amongst the most effective calculations, have been broadly used to find the inactive semantic examples in content accumulations. In any case, one key shortcoming of point models is that they require archives with certain length to give dependable measurements adversary producing intelligent themes. In Twitter, the clients’ tweets are for the most part short and loud. Perceptions of word events are immeasurable for theme models. The RAKE algorithm shows better performance than TextRank, Supervised Learning.  Â