다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Over the last decade industrial and academic communities have increased their focus on sentiment analysis techniques, especially applied to tweets. State-of-the-art results have been recently achieved using language models trained from scratch on corpora made up exclusively of tweets, in order to better handle the Twitter jargon. This work aims to introduce a different approach for Twitter sentiment analysis based on two steps. Firstly, the tweet jargon, including emojis and emoticons, is transformed into plain text, exploiting procedures that are language-independent or easily applicable to different languages. Secondly, the resulting tweets are classified using the language model BERT, but pre-trained on plain text, instead of tweets, for two reasons: (1) pre-trained models on plain text are easily available in many languages, avoiding resource- and time-consuming model training directly on tweets from scratch; (2) available plain text corpora are larger than tweet-only ones, therefore allowing better performance. A case study describing the application of the approach to Italian is presented, with a comparison with other Italian existing solutions. The results obtained show the effectiveness of the approach and indicate that, thanks to its general basis from a methodological perspective, it can also be promising for other languages.

https://www.mdpi.com/1424-8220/21/1/133/pdf

An Effective BERT-Based Pipeline for Twitter Sentiment Analysis: A Case Study in Italian.

Social media offer a big amount of information, to exploit in many fields of research. However, while methods for Natural Language Processing are being developed with good results when applied to well-formed datasets made of written text with a clear syntax, these sources present text written in informal language, unstructured syntax, and with peculiar symbols; therefore, particular approaches are required for text processing in this case. In this paper, the task of sentiment analysis of tweets is regarded. In particular, in order to avoid noise constituted by some web constructs like URLs and mentions and by other text fragments, and to exploit information hidden in symbols like emoticons, emojis and hashtags, the pre-processing of tweets is analyzed. More in detail, a number of experiments, performed by a state-of-the-art classification model (BERT), are designed, to evaluate many currently available operations for pre-processing tweets, in terms of the statistical significance of their influence on sentiment analysis performances. Moreover, available data in two languages are considered, i.e., English and Italian, in order to also evaluate dependence on the language. Results allow to individuate the most convenient strategy to pre-process tweets, and thus to improve the state of the art in both languages for the considered task of sentiment analysis.

Multilingual evaluation of pre-processing for BERT-based sentiment analysis of tweets

The analysis of sentiments is essential in identifying and classifying opinions regarding a source material that is, a product or service. The analysis of these sentiments finds a variety of applications like product reviews, opinion polls, movie reviews on YouTube, news video analysis, and health care applications including stress and depression analysis. The traditional approach of sentiment analysis which is based on text involves the collection of large textual data and different algorithms to extract the sentiment information from it. But multimodal sentimental analysis provides methods to carry out opinion analysis based on the combination of video, audio, and text which goes a way beyond the conventional text‐based sentimental analysis in understanding human behaviors. The remarkable increase in the use of social media provides a large collection of multimodal data that reflects the user's sentiment on certain aspects. This multimodal sentimental analysis approach helps in classifying the polarity (positive, negative, and neutral) of the individual sentiments. Our work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve human–machine interaction and challenges involved in analyzing them. A detailed survey on sentimental dataset, feature extraction algorithms, data fusion methods, and efficiency of different classification techniques are presented in this work.

Multimodal sentimental analysis for social media applications: A comprehensive review

Data analytics and its associated applications have recently become impor-tant fields of study. The subject of concern for researchers now-a-days is a massive amount of data produced every minute and second as people con-stantly sharing thoughts, opinions about things that are associated with them. Social media info, however, is still unstructured, disseminated and hard to handle and need to be developed a strong foundation so that they can be utilized as valuable information on a particular topic. Processing such unstructured data in this area in terms of noise, co-relevance, emoticons, folksonomies and slangs is really quite challenging and therefore requires proper data pre-processing before getting the right sentiments. The dataset is extracted from Kaggle and Twitter, pre-processing performed using NLTK and Scikit-learn and features selection and extraction is done for Bag of Words (BOW), Term Frequency (TF) and Inverse Document Frequency (IDF) scheme. 
For polarity identification, we evaluated five different Machine Learning (ML) algorithms viz Multinomial Naive Bayes (MNB), Logistic Regression (LR), Decision Trees (DT), XGBoost (XGB) and Support Vector Machines (SVM). We have performed a comparative analysis of the success for these algorithms in order to decide which algorithm works best for the given data-set in terms of recall, accuracy, F1-score and precision. We assess the effects of various pre-processing techniques on two datasets; one with domain and other not. It is demonstrated that SVM classifier outperformed the other classifiers with superior evaluations of 73.12% and 94.91% for accuracy and precision respectively. It is also highlighted in this research that the selection and representation of features along with various pre-processing techniques have a positive impact on the performance of the classification.  The ultimate outcome indicates an improvement in sentiment classification and we noted that pre-processing approaches obviously suggest an improvement in the efficiency of the classifiers.

/pdf/influence-of-pre-processing-strategies-on-the-performance-of-18xaz9at2d.pdf

Influence of Pre-Processing Strategies on the Performance of ML Classifiers Exploiting TF-IDF and BOW Features

In the big data era, data is made in real-time or closer to real-time. Thus, businesses can utilize this evergrowing volume of data for the data-driven or information-driven decision-making process to improve their businesses. Social media, like Twitter, generates an enormous amount of such data. However, social media data are often unstructured and difficult to manage. Hence, this study proposes an effective text data preprocessing technique and develop an algorithm to train the Support Vector Machine (SVM), Deep Learning (DL) and Naive Bayes (NB) classifiers to process Twitter data. We develop an algorithm that weights the sentiment score in terms of weight of hashtag and cleaned text. In this study, we (i) compare different preprocessing techniques on the data collected from Twitter using various techniques such as (stemming, lemmatization and spelling correction) to obtain the efficient method (ii) develop an algorithm to weight the scores of the hashtag and cleaned text to obtain the sentiment. We retrieved N=1,314,000 Twitter data, and we compared the popularity of two products, Google Now and Amazon Alexa. Using our data preprocessing algorithm and sentiment weight score algorithm, we train SVM, DL, NB models. The results show that stemming technique performed best in terms of computational speed. Additionally, the accuracy of the algorithm was tested against manually sorted sentiments and sentiments produced before text data preprocessing. The result demonstrated that the impact produced by the algorithm was close to the manually annotated sentiments. In terms of model performance, the SVM performed better with the accuracy of 90.3%, perhaps, due to the unstructured nature of Twitter data. Previous studies used conventional techniques; hence, no precise methods were utilized on cleaning the text. Therefore, our approach confirms that proper text data preprocessing technique plays a significant role in the prediction accuracy and computational time of the classifier when using the unstructured Twitter data.

Effective Text Data Preprocessing Technique for Sentiment Analysis in Social Media Data

Technology has turned into a fundamental piece of everybody's life. Social media technology is already used widely by the public to speak out once mind openly. This data can be leveraged to have a better understanding of the current state of decision making. However, Twitter data is highly unstructured. Sentiment analysis can be applied to such health-related data to extract useful information regarding public opinion. The aim of the research is to understand (i) the correlation between Deep Learning versus lexical and semantic-based sentiment prediction methods, (ii) the sentiment prediction accuracy of these methods on manually annotated sentiment dataset (iii) domain-specific knowledge on accuracy of the sentiment prediction methods, and (iv) to utilize Twitterbased sentiment to understand the influence of telemedicine in regards to heart attack and epilepsy. Four sentiment prediction methods are utilized for the research; Lexical and Semantic-based (Valence Aware Dictionary and Sentiment Reasoner (VADER) and TextBlob) and Deep Learning based (Long Short Term Memory (LSTM) and sentiment model from Stanford CoreNLP). The dataset that we retrieved consists of 1.84 million old health-related tweets. Our finding suggests that lexical and semantic-based methods for sentiment prediction offer better accuracy than Deep Learning methods; when a large enough and evenly distributed training dataset is not available. We observed that domain-specific knowledge affects the prediction accuracy of sentiment, mainly when the target text contains more domain-specific words. Sentiment prediction on Twitter data can be utilized to understand the demographic distribution of sentiment. In our case, we observed that telemedicine has a high number of positive sentiment. It is still in its infancy and has not spread to a broader demographic.

An Analysis on Use of Deep Learning and Lexical-Semantic Based Sentiment Analysis Method on Twitter Data to Understand the Demographic Trend of Telemedicine

A growing number of people suffer from dementia and need to be monitored for safety. Options are nursing homes or home monitoring through smart devices. This article aims to provide an overview of available technology for indoor and outdoor monitoring. We also propose a framework through which current and future systems can be evaluated consisting of Data, Transfer and Storage and Monitoring (DTSM). We analyze wearable devices, means of data collection and data transfer, data accessibility during storage and throughout analysis. We evaluate the DTSM framework in terms of completeness and acceptance. 30 state of the art research papers are classified to identify systems components, evaluated against the DTSM taxonomy. This research contributes to future systems development underpinning wearable devices for the purpose of tracking human activities.

Wearable Devices for Monitoring Dementia Sufferers: A Review and Framework for Discussion

Materialized views are logically excess stored query results in SQL-oriented databases. This technology can significantly improve the performance of database systems. Although the idea of materialized views came up in the 1980s, only three database management systems, i.e. DB2, Oracle, SQL Server, have been successfully developed completely enough with materialized views so far. The barrier lies in building a module that can incrementally update the materialized views automatically, which corresponds to data changes in the base tables. This paper presents the algorithm to incrementally update the materialized views with inner join, focusing on one with aggregate functions, and building of a program that automatically generates codes inPL/pgSQL for triggers, which can undertake synchronous incremental updates of the materialized views in PostgreSQL.

Synchronous incremental update of materialized views for PostgreSQL

Materialized views can help improve query execution speed dramatically using full or part of stored precalculated query results. Incremental maintenance takes materialized views up-to-date adjusting them accordingly to the changes in related base tables. It is often more effective than a full refresh replacing materialized view tables by the new query execution result. Asynchronous maintenance, which brings the materialized views to the actual state, is not a constituent of the transaction making changes in the base tables. Most of the published works are dedicated to synchronous incremental updating of views, algorithms for which require accessing the pre-update state of base tables and cannot be applied directly to asynchronous updates which are performed on the post-update state. A few works are devoted to asynchronous maintenance of views, either restrict changes in only one of base tables or assume there is only one base table, which is impractical, either is wrong, either provides too high level and complex incremental update algorithms or can be implemented only if the database management system supports data versioning at the table and row levels. In this paper, we propose a solution for the asynchronous incremental update of views which can be implemented with any database management systems. We collect changes in base tables, access the pre-update state of base tables exploiting the condensing process and apply the pre-update incremental maintenance algorithms for asynchronous maintenance on the post-update state of base tables considering the specifics of asynchronous maintenance. It is applicable for SPJ queries with inner joins, queries with inner joins and aggregations. We also build a prototype and provide experiments on automatic generating source codes in C to collect changes in base tables and to perform the asynchronous incremental update of materialized views in PostgreSQL

/pdf/a-new-solution-for-asynchronous-incremental-maintenance-of-9zca575feq.pdf

Nguyen Tran Quoc Vinh

Papers

Effective Text Data Preprocessing Technique for Sentiment Analysis in Social Media Data

An Analysis on Use of Deep Learning and Lexical-Semantic Based Sentiment Analysis Method on Twitter Data to Understand the Demographic Trend of Telemedicine

Wearable Devices for Monitoring Dementia Sufferers: A Review and Framework for Discussion

Synchronous incremental update of materialized views for PostgreSQL

A new solution for asynchronous incremental maintenance of materialized views