Search

Classical Chinese poetry has been increasingly popular in recent years, and modeling its topic is quite a promising area of research. Chinese poems have the characteristic of short in length, but traditional topic models perform poorly when faced with short texts due to the text sparsity. Therefore, topic model should be improved to satisfy the scenario of classical Chinese poems. In this paper, a relational background knowledge boosting based topic model (RBKBTM) was proposed to overcome the text sparsity of Chinese poems. We incorporated background information into the model, which expanded the text content from the semantic perspective. The background knowledge was combined using word embedding and TextRank and was then fed into the core computing process. Subsequently, a new sampling formula was derived. Our proposed model was tested on three different tasks using three different datasets. The results demonstrate that the incorporated background knowledge can effectively overcomes text sparsity, improving the performance and effectiveness of the topic model. [ABSTRACT FROM AUTHOR]

Feature location is a technique for determining source code that implements specific features in software. It developed to help minimize effort on program comprehension. The main challenge of feature location research is how to bridge the gap between abstract keywords in use cases and detail in source code. The use case scenarios are software requirements artifacts that state the input, logic, rules, actor, and output of a function in the software. The sentence on use case scenario is sometimes described another sentence in other use case scenario. This study contributes to creating expansion queries in feature locations by finding the relationship between use case scenarios. The relationships include inner association, outer association and intratoken association. The research employs latent Dirichlet allocation (LDA) to create model topics on source code. Query expansion using inner, outer and intratoken was tested for finding feature locations on a Java-based open-source project. The best precision rate was 50%. The best recall was 100%, which was found in several use case scenarios implemented in a few files. The best average precision rate was 16.7%, which was found in inner association experiments. The best average recall rate was 68.3%, which was found in all compound association experiments. [ABSTRACT FROM AUTHOR]

Gaining a complete picture of the activity in a city using vast data sources is challenging yet potentially very valuable. One such source of data is Twitter which generates millions of short spatio-temporally localized messages that, as a collection, have information on city regions and many forms of city activity. The quantity of data, however, necessitates summarization in a way that makes consumption by an observer efficient, accurate, and comprehensive. We present a two-step process for analyzing geotagged twitter data within a localized urban environment. The first step involves an efficient form of latent Dirichlet allocation, using an expectation maximization, for topic content summarization of the text information in the tweets. The second step involves spatial and temporal analysis of information within each topic using two complimentary metrics. These proposed metrics characterize the distributional properties of tweets in time and space for all topics. We integrate the second step into a graphical user interface that enables the user to adeptly navigate through the space of hundreds of topics. We present results of a case study of the city of Madrid, Spain, for the year 2011 in which both large-scale protests and elections occurred. Our data analysis methods identify these important events, as well as other classes of more mundane routine activity and their associated locations in Madrid.

Human free association (FA) norms are believed to reflect thestrength of links between words in the lexicon of an averagespeaker. Large-scale FA norms are commonly used as a datasource both in psycholinguistics and in computational mod-eling. However, few studies aim to analyze FA norms them-selves, and it is not known what are the most important factorsthat guide speakers’ lexical choices in the FA task. Here, wefirst provide a statistical analysis of a large-scale data set ofEnglish FA norms. Second, we argue that such analysis caninform existing computational models of semantic memory,and present a case study with the topic model to support thisclaim. Based on our analysis, we provide the topic model withdictionary-based knowledge about word synonymy/antonymy,and demonstrate that the resulting model predicts human FAresponses better than the topic model without this information.

Quantitative text analysis is a set of procedures for grouping documents and the words and expressions that make up the content of documents, supported by statistical methods and tools. Its main advantage is that in addition to the information that can be extracted from numerical data, it provides a solution for accessing additional information that previously seems unavailable. Thus, text analysis is most commonly used where the text contains more information than could be obtained from quantified data. Text and content analysis is today one of the most exciting and focused areas of data mining and data analysis, both in terms of mathematical, statistical, methodological, and software fit. In this study, latent Dirichlet allocation (LDA) is presented as a possible methodological approach through a concrete example. The primary aim of the article is to show that text analysis can provide long-term and novel perspectives in the fields of management science. [ABSTRACT FROM AUTHOR]

Predicting clinical patients' vital signs is a leading critical issue in intensive care units (ICUs) related studies. Early prediction of the mortality of ICU patients can reduce the overall mortality and cost of complication treatment. Some studies have predicted mortality based on electronic health record (EHR) data by using machine learning models. However, the semi-structured data (i.e., patients' diagnosis data and inspection reports) is rarely used in these models. This study utilized data from the Medical Information Mart for Intensive Care III. We used a Latent Dirichlet Allocation (LDA) model to classify text in the semi-structured data of some particular topics and established and compared the classification and regression trees (CART), logistic regression (LR), multivariate adaptive regression splines (MARS), random forest (RF), and gradient boosting (GB). A total of 46,520 ICU Patients were included, with 11.5% mortality in the Medical Information Mart for Intensive Care III group. Our results revealed that the semi-structured data (diagnosis data and inspection reports) of ICU patients contain useful information that can assist clinical doctors in making critical clinical decisions. In addition, in our comparison of five machine learning models (CART, LR, MARS, RF, and GB), the GB model showed the best performance with the highest area under the receiver operating characteristic curve (AUROC) (0.9280), specificity (93.16%), and sensitivity (83.25%). The RF, LR, and MARS models showed better performance (AUROC are 0.9096, 0.8987, and 0.8935, respectively) than the CART (0.8511). The GB model showed better performance than other machine learning models (CART, LR, MARS, and RF) in predicting the mortality of patients in the intensive care unit. The analysis results could be used to develop a clinically useful decision support system. [ABSTRACT FROM AUTHOR]

Background: Research publications related to the novel coronavirus disease COVID-19 are rapidly increasing. However, current online literature hubs, even with artificial intelligence, are limited in identifying the complexity of COVID-19 research topics. We developed a comprehensive Latent Dirichlet Allocation (LDA) model with 25 topics using natural language processing (NLP) techniques on PubMed® research articles about “COVID.” We propose a novel methodology to develop and visualise temporal trends, and improve existing online literature hubs.Our results for temporal evolution demonstrate interesting trends, for example, the prominence of “Mental Health” and “Socioeconomic Impact” increased, “Genome Sequence” decreased, and “Epidemiology” remained relatively constant. Applying our methodology to LitCovid, a literature hub from the National Center for Biotechnology Information, we improved the breadth and depth of research topics by subdividing their pre-existing categories. Our topic model demonstrates that research on “masks” and “Personal Protective Equipment (PPE)” is skewed toward clinical applications with a lack of population-based epidemiological research.

Background: One of the most comprehensive approaches to depression is the biopsychosocial model. From this wider perspective, social sciences have criticized the reductionist biomedical discourse, which has been dominating expert discourses for a long time. As these discourses determine the horizon of attributions and interventions, their lay interpretation plays a central role in the coping with depression. Methods: In order to map these patterns, online depression forums are analyzed with natural language processing methods, where computational tools are complemented with a qualitative approach. Latent Dirichlet Allocation topic model of depression-related posts from the most popular English-speaking online health discussion forums (N = ~70 000) reveals the monolog (attributions and self-disclosures) and interactive (consultations and quasi-therapeutic interactions) patterns. Results: Following the evaluation of various models 18 topics were differentiated: attributions referring to health, family, partnership and work issues; self-disclosures referring to contemplations, introducing the experience of suffering and well-being, along with diaries of everyday activities and hardships; consultations about psychotherapies, classifications, drugs and the experience; and quasi-therapeutic interactions relying on unconditional positive regards, recovery helpers experience or spirituality. These topics were evaluated from the perspective of the biopsychosocial model: the weight of each dimension was measured along with the discursive function. Conclusions: Biomedical discourse is underrepresented in lay discussions, while psychological discourse plays an overall dominant role. Even if actors are initially aware of the social mechanisms contributing to depression, they neglect these factors when it comes to considering the countermeasures.

We propose two new topic modeling methods for sequential documents based on hybrid inter-document topic dependency. Topic modeling for sequential documents is the basis of many attractive applications such as emerging topic clustering and novel topic detection. For these tasks, most of the existing models introduce inter-document dependencies between topic distributions. However, in a real situation, adjacent emerging topics are often intertwined and mixed with outliers. These single-dependency based models have difficulties in handling the topic evolution in such multi-topic and outlier mixed sequential documents. To solve this problem, our first method considers three kinds of topic dependencies for each document to handle its probabilities of belonging to a fading topic, an emerging topic, or an independent topic. Secondly, we extend our first method by considering fine-grained dependencies in a given context for more complex topic evolution sequences. Our experiments conducted on six standard datasets on topic modeling show that our proposals outperform state-of-the-art models in terms of the accuracy of topic modeling, the quality of topic clustering, and the effectiveness of outlier detection. [ABSTRACT FROM AUTHOR]

Predicting clinical patients’ vital signs is a leading critical issue in intensive care units (ICUs) related studies. Early prediction of the mortality of ICU patients can reduce the overall mortality and cost of complication treatment. Some studies have predicted mortality based on electronic health record (EHR) data by using machine learning models. However, the semi-structured data (i.e., patients’ diagnosis data and inspection reports) is rarely used in these models. This study utilized data from the Medical Information Mart for Intensive Care III. We used a Latent Dirichlet Allocation (LDA) model to classify text in the semi-structured data of some particular topics and established and compared the classification and regression trees (CART), logistic regression (LR), multivariate adaptive regression splines (MARS), random forest (RF), and gradient boosting (GB). A total of 46,520 ICU Patients were included, with 11.5% mortality in the Medical Information Mart for Intensive Care III group. Our results revealed that the semi-structured data (diagnosis data and inspection reports) of ICU patients contain useful information that can assist clinical doctors in making critical clinical decisions. In addition, in our comparison of five machine learning models (CART, LR, MARS, RF, and GB), the GB model showed the best performance with the highest area under the receiver operating characteristic curve (AUROC) (0.9280), specificity (93.16%), and sensitivity (83.25%). The RF, LR, and MARS models showed better performance (AUROC are 0.9096, 0.8987, and 0.8935, respectively) than the CART (0.8511). The GB model showed better performance than other machine learning models (CART, LR, MARS, and RF) in predicting the mortality of patients in the intensive care unit. The analysis results could be used to develop a clinically useful decision support system.

This study aims to find the structure of social disussion on government ‘Senior job program’ by analyzing 1107 newspaper articles on ‘senior job program’ from 11 major newspaper articles and 8 financial newspapers. Topic modeling via latent dirichlet allocation model was employed for analysis and as result, 5 latent topics were extracted as follows : general information, local government project propaganda, senior life related issues, employment creation effect and market relations. Until 2015, most of the articles focused on the first two topics, indicating not much discourse was formed concerning the characteristics of the program. However, after 2015, the third topic started to increase and after the launch of Moon Jae In government, there has been a drastic increase in the employment creation related topic indicating that current social discourse mirrored by the media is definitely focused on employment creation aspect of senior job program. Based on the result, this study suggests the necessity to increase the quality and also enhance employment aspects of Senior job program. [ABSTRACT FROM AUTHOR]

This study tests the effect of gubernatorial policy agendas on state budgetary choices. Governors are commonly perceived as state policy leaders, but lack direct legislative authority and depend on the law makers to pass bills and present them for signature. The theory posits that governors nonetheless possess several formal and informal tools that are used to overcome this institutional disadvantage and successfully pursue their policy goals. Gubernatorial policy priorities in this study are extracted from public speeches using unsupervised machine learning. Their influence on state spending choices in different policy areas is tested through panel data analysis of all states from 2007 through 2015. Empirical findings reveal that the effect of executive agendas is more pronounced in the area of transportation infrastructure and public safety—potentially due to lower levels of conflict and concentrated benefits, which eases deal making with law makers. Governors are also more persistent with policy proposals that are more important for reelection. Related Articles: Adams, Brian E. 2016. "Assessing the Merits of Decentralization: A Framework for Identifying the Causal Mechanisms Influencing Policy Outcomes." Politics & Policy 44 (5): 820‐849. https://doi.org/10.1111/polp.12172 Heidbreder, Brianne. 2012. "Agenda Setting in the States: How Politics and Policy Needs Shape Gubernatorial Agendas." Politics & Policy 40 (2): 296‐319. https://doi.org/10.1111/j.1747-1346.2012.00345.x Patrick, Barbara. 2012. "Fiscal Federalism, Performance Policies, and Education Reforms: Are States Using Performance Policies to Improve Workforce Quality?" Politics & Policy 40 (4): 593‐628. https://doi.org/10.1111/j.1747-1346.2012.00370.x [ABSTRACT FROM AUTHOR]

With the proliferation of the Internet and the rapid growth of electronic articles, text classification has become one of the key and important tools for data organization and management. In text classification a set of basic knowledge is provided to the system by learning. Then, new input documents enter to one of the subject groups. In health literature due to wide variety of topics, preparing such a set of early education is a very time consuming and costly task. The purpose of this article is to present a hybrid model of learning (supervised and unsupervised) for the subject classification of health scientific products that performs the classification operation without the need for an initial labeled set. To extract the thematic model of health science texts from 2009 to 2019 at PubMed database, data mining and text mining were performed using machine learning. Based on Latent Dirichlet Allocation model, the data were analyzed and then the Support Vector Machine was used to classify the texts. In the findings of this study, the model was introduced in three main steps. In data preprocessing, the unnecessary words were eliminated from the data set and the accuracy of the proposed model increased. In the second step, the themes in the texts were extracted using the Latent Dirichlet Allocation method, and as a basic training set in step 3, the data were backed up by the Support Vector Machine algorithm and the classifier learning was performed with the help of these topics. Finally, with the help of the classification, the subject of each document was identified. The results showed that the proposed model can build a better classification by combining unsupervised clustering properties and prior knowledge of the samples. Clustering on labeled samples with a specific similarity criterion merges related texts with prior knowledge, and the learning algorithm teaches classification by supervisory method. Combining classification and clustering can increase the accuracy of classification of health texts. [ABSTRACT FROM AUTHOR]

LDA is based on the bag-of-words, which simplifies the complexity of modeling, but makes the semantic coherence of topics poor, and text representation ability is not strong. To solve this problem, this paper proposed the semantic distribution similarity based topic model. This model used GPU (generalized Pólya urn) model to add word-word and document-topic semantic distribution similarity to guide topic modeling under the framework of EM (expectation maximization) algorithm, which weakened the effect of bag-of-words hypothesis on topics from the semantic association level. Experiments on four public datasets show that the semantic distribution similarity based topic model is superior to the currently popular topic modeling algorithms in terms of topic semantic coherence and text classification accuracy, and the model improves the convergence speed and topic accuracy. [ABSTRACT FROM AUTHOR]