To help researchers conduct a systematic review or meta-analysis as efficiently and transparently as possible, we designed a tool to accelerate the step of screening titles and abstracts. For many tasks—including but not limited to systematic reviews and meta-analyses—the scientific literature needs to be checked systematically. Scholars and practitioners currently screen thousands of studies by hand to determine which studies to include in their review or meta-analysis. This is error prone and inefficient because of extremely imbalanced data: only a fraction of the screened studies is relevant. The future of systematic reviewing will be an interaction with machine learning algorithms to deal with the enormous increase of available text. We therefore developed an open source machine learning-aided pipeline applying active learning: ASReview. We demonstrate by means of simulation studies that active learning can yield far more efficient reviewing than manual reviewing while providing high quality. Furthermore, we describe the options of the free and open source research software and present the results from user experience tests. We invite the community to contribute to open source projects such as our own that provide measurable and reproducible improvements over current practice. It is a challenging task for any research field to screen the literature and determine what needs to be included in a systematic review in a transparent way. A new open source machine learning framework called ASReview, which employs active learning and offers a range of machine learning models, can check the literature efficiently and systemically.

/pdf/an-open-source-machine-learning-framework-for-efficient-and-1m6m7lcle5.pdf

An open source machine learning framework for efficient and transparent systematic reviews

To help researchers conduct a systematic review or meta-analysis as efficiently and transparently as possible, we designed a tool (ASReview) to accelerate the step of screening titles and abstracts. For many tasks - including but not limited to systematic reviews and meta-analyses - the scientific literature needs to be checked systematically. Currently, scholars and practitioners screen thousands of studies by hand to determine which studies to include in their review or meta-analysis. This is error prone and inefficient because of extremely imbalanced data: only a fraction of the screened studies is relevant. The future of systematic reviewing will be an interaction with machine learning algorithms to deal with the enormous increase of available text. We therefore developed an open source machine learning-aided pipeline applying active learning: ASReview. We demonstrate by means of simulation studies that ASReview can yield far more efficient reviewing than manual reviewing, while providing high quality. Furthermore, we describe the options of the free and open source research software and present the results from user experience tests. We invite the community to contribute to open source projects such as our own that provide measurable and reproducible improvements over current practice.

/pdf/open-source-software-for-efficient-and-transparent-reviews-3kt5hozvi6.pdf

Open Source Software for Efficient and Transparent Reviews

In the emerging peer-to-peer (P2P) lending industry, risks such as credit risk and default risk will bring huge losses to online lending platforms and investors. Therefore, it is necessary to design a reasonable evaluation index system of credit risk to scientifically evaluate the risk level of borrowers. This paper studies the design of comprehensive evaluation index system for P2P credit risk of “three rural” (i.e., agriculture, rural areas and farmers) borrowers. Concretely, we construct the feature set for P2P credit risk of “three rural” borrowers. Based on the traditional index system, we add the static indexes specific to the agriculture-related borrowers and the dynamic indexes reflect the Internet as the preliminary indexes of the feature set and select the borrowers data of the “Pterosaur loan” platform as the research sample. Then, 35 borrower credit features are extracted as a feature set of credit risk. Then, we present a two-stage feature selection method based on filter and wrapper to select the main features from 35 initial borrower credit features. In the stage of filter, three filter methods are used to calculate the importance of the unbalanced features. In the stage of wrapper, a Lasso-logistic method is proposed to filter the feature subset through heuristic search algorithm. In the end, 21 main independent features are selected according to the classification accuracy, which constitute the evaluation index system of credit risk of “three rural” borrowers.

Design of comprehensive evaluation index system for P2P credit risk of “three rural” borrowers

Stock price prediction is a hot topic and traditional prediction methods are usually based on statistical and econometric models. However, these models are difficult to deal with nonstationary time series data. With the rapid development of the internet and the increasing popularity of social media, online news and comments often reflect investors’ emotions and attitudes toward stocks, which contains a lot of important information for predicting stock price. This paper aims to develop a stock price prediction method by taking full advantage of social media data.,This study proposes a new prediction method based on deep learning technology, which integrates traditional stock financial index variables and social media text features as inputs of the prediction model. This study uses Doc2Vec to build long text feature vectors from social media and then reduce the dimensions of the text feature vectors by stacked auto-encoder to balance the dimensions between text feature variables and stock financial index variables. Meanwhile, based on wavelet transform, the time series data of stock price is decomposed to eliminate the random noise caused by stock market fluctuation. Finally, this study uses long short-term memory model to predict the stock price.,The experiment results show that the method performs better than all three benchmark models in all kinds of evaluation indicators and can effectively predict stock price.,In this paper, this study proposes a new stock price prediction model that incorporates traditional financial features and social media text features which are derived from social media based on deep learning technology.

/pdf/a-stock-price-prediction-method-based-on-deep-learning-3t5xqhqrvz.pdf

A stock price prediction method based on deep learning technology

With 20 million presents every day, outcast applications are a guideline clarification behind the reputation and addictiveness of Facebook. Lamentably, developers have comprehended the ability of using applications for spreading malware and spam. The issue is starting at now major, as we find that no under 13% of uses in our dataset are threatening to date, the investigation gather has focused on perceiving noxious posts and campaigns. In this paper, we suggest the conversation starter: given a Facebook application, would we have the capacity to pick if it is malignant? Our key duty is in making FRAppE Facebook's Rigorous Application Evaluator apparently the foremost instrument focused on finding dangerous applications on Facebook. To make FRAppE, we use information amassed by watching the posting behavior of 111K Facebook applications seen across more than 2.2 million customers on Facebook. In the first place, we perceive a game plan of components that aides us perceive noxious applications from kindhearted ones. For example, we locate that vindictive applications oftentimes confer names to various applications, and they usually request less assents than positive applications. Second, using these perceiving features, we display that FRAppE can recognize malignant applications with 99.5% precision, with no false positives and a low false negative rate (4.1%). Finally, we research the natural arrangement of noxious Facebook applications and see segments that these applications use to spread inquisitively, we locate that various applications plot and reinforce each other; in our dataset, we find 1,584 applications enabling the viral causing of 3,723 distinct applications through their posts. Whole deal, we view FRAppE as a phase towards making a free protect canine for application evaluation and situating, to alert Facebook customers before presenting applications.

Towards Online Spam Filtering In Social Networks

Multi-co-training for document classification using various document representations: TF–IDF, LDA, and Doc2Vec

The Vehicle Dependability Study (VDS) is a survey study on customer satisfaction for vehicles that have been sold for three years. VDS data analytics plays an important role in the vehicle development process because it can contribute to enhancing the brand image and sales of an automobile company by properly reflecting customer requirements retrieved from the analysis results when developing the vehicle’s next model. Conventional approaches to analyzing the voice of customers (VOC) data, such as VDS, have focused on finding the mainstream of customer responses, many of which are already known to the enterprise. However, detecting and visualizing notable opinions from a large amount of VOC data are important in responding to customer complaints. In this study, we propose a framework for identifying unusual but significant customer responses and frequently used words therein based on distributed document representation, local outlier factor, and TF–IDF methods. We also propose a procedure that can provide useful information to vehicle engineers by visualizing the main results of the framework. This unusual customer response detection and visualization framework can accelerate the efficiency and effectiveness of many VOC data analytics.

Unusual customer response identification and visualization based on text mining and anomaly detection

This study develops a text spam filtering system for Facebook based on two variable categories: keywords learned from Instagram and meta-information of Facebook posts. Since there is no explicit labels for spam/ham posts, we utilize hash tags in Instagram to train classification models. In addition, the filtering accuracy is enhanced by considering meta-information of Facebook posts. To verify the proposed filtering system, we conduct an empirical experiment based on a total of 1,795,067 and 761,861 Facebook and Instagram documents, respectively. Employing random forest as a base classification algorithm, experimental result shows that the proposed filtering system yield 99% and 98% in terms of filtering accuracy and F1-measure, respectively. We expect that the proposed filtering scheme can be applied other web services suffering from massive spam posts but no explicit spam labels are available.

https://www.koreascience.kr:443/article/JAKO201718837035674.pdf

Deokseong Seo

Papers

Multi-co-training for document classification using various document representations: TF–IDF, LDA, and Doc2Vec

Unusual customer response identification and visualization based on text mining and anomaly detection

Facebook Spam Post Filtering based on Instagram-based Transfer Learning and Meta Information of Posts