دانلود رایگان مقاله انگلیسی ردیابی رسانه های اجتماعی متعدد برای پیش بینی رویدادها در بازار سهام به همراه ترجمه فارسی
عنوان فارسی مقاله: | ردیابی رسانه های اجتماعی متعدد برای پیش بینی رویدادها در بازار سهام |
عنوان انگلیسی مقاله: | Tracking Multiple Social Media for Stock Market Event Prediction |
رشته های مرتبط: | علوم اقتصادی، اقتصاد مالی و اقتصاد پولی |
فرمت مقالات رایگان | مقالات انگلیسی و ترجمه های فارسی رایگان با فرمت PDF میباشند |
کیفیت ترجمه | کیفیت ترجمه این مقاله متوسط میباشد |
نشریه | اسپرینگر – Springer |
کد محصول | f399 |
مقاله انگلیسی رایگان (PDF) |
دانلود رایگان مقاله انگلیسی |
ترجمه فارسی رایگان (PDF) |
دانلود رایگان ترجمه مقاله |
خرید ترجمه با فرمت ورد |
خرید ترجمه مقاله با فرمت ورد |
جستجوی ترجمه مقالات | جستجوی ترجمه مقالات علوم اقتصادی |
بخشی از ترجمه فارسی مقاله: 1. مقدمه 2. اثر مرتبط |
بخشی از مقاله انگلیسی: 1 Introduction Predictions concerning financial markets are complicated by their inherent volatility. Capturing signals of this volatility and providing proper estimates about ‘market flips’ is of prime interest to economists. This problem has attracted great interest from researchers in diverse disciplines such as economics, statistics and data science. Consequently this has led to a wide variety of methods aimed at modeling stock markets [11, 16, 17, 20, 23]. In most of the traditional approaches, researchers characterize the stock market by the historical records of prices and try to find signatures that indicate rising or falling prices based on this historical time series. However, such financial time series methods are generally incognizant of human indicators, such as public reaction, and have frequently been found wanting in their accuracy at predicting sudden, large changes in market value [4]. Recently, with the pervasive growth of social media [6, 14] which allow individuals to readily express their sentiments [21], views and concerns, real-time mining of such factors has become possible. Furthermore, different aspects of public sentiment can now be extracted by analyzing multiple social networks. In this paper, we collect and analyze global search trend data from Google, archived news articles from Bloomberg News and relevant tweets from Twitter. Using unsupervised methods, we extract features from these publicly available data sources. Using these features, we design a set of experiments to investigate the correlations between human behavior and market fluctuations in South American markets. With this analysis, we propose models that predict large changes (events) in market value using the most informative extracted factors. To be specific, given these three data sources at day d and historical stock prices for a market, our proposed models attempt to predict the stock market value of at least day d + 1. The key contributions of this paper are: – We propose a systematic analysis of Google Search Trends, Bloomberg News and Twitter to gather information about market trends and quantify these social media trends. – We identify burst features from Twitter and further group burst features into burst events. We also investigate and find the correlations of these burst events with market trends. – We present Delta Naive Bayes Model to predict finance market fluctuations by fusing multiple social media sources. Though there have been earlier attempts at investigating combinations of sources for finance related applications [12, 19], most of the work has focused on surveying datasets. In that respect, to the best our knowledge, our work is the first not only to compare sources but also to propose predictive models that leverage multiple sources. – Finally, we present our findings about the underlying cross-correlation among market indicators extracted from multiple social media sources and extensively analyze the information from each data source. 2 Related Work In this section we review a few works related to the fields of financial time series analysis, modeling of financial markets and extraction of features from online data streams. Financial Time Series Analysis Financial time series analysis has been one of the most popular approaches to market modeling. Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models [5] have been widely applied in the financial domain since the 1980s. Clustering algorithms have been applied to redescribe time series [11] and identify temporally correlated stocks [1], methods which we have employed in our data processing. More recently, [17] proposed information dissipation length as a leading indicator to measure global instability Correlation with Social Media With the recent development and prevalence of big data platforms [25, 24], adopting data mining tasks on online social networks has been shown to produce state-of-the-art results. There have been a number of exploratory analyses correlating social media with stock markets. [16] found a correlation between transaction volumes of top companies and Google search volumes of those companies’ names. [12] investigated the correlation of search query volume and the Dow Jones Industrial Average (DJIA) and found that a higher search volume of certain finance terms indicates lower DJIA prices. Further, [15] found that trading strategies based on the volumes of 98 keywords from Google Search Trends outperformed random investment with respect to overall turnover. Recently, [13] study the ”co-movements” between stock prices and news articles for stock market prediction. [4] calculated public sentiment from Twitter and found the “calm” sentiment curve has an especially strong correlation with DJIA values. [20] found that the number of connected components in a constrained subgraph within time-constrained graphs has high correlation with traded volume. In this paper, we build on the research that suggests that aggregate search volume and sudden changes in sentiment across social networks are correlated with financial market performance by combining these factors in a unified prediction framework. Feature Fusion With respect to fusion methods, [10] proposed the popular Kalman Filter approach for linear filtering and prediction problems which measures multiple sequential sensors to estimate a system’s dynamic states. The naive Bayes classifier has been recognized as an effective model which can estimate class labels for multi-dimensional features based on maximum posterior probabilities. Hidden Markov models have been applied successfully for temporal pattern recognition in areas such as sequential images [27]. In our experiment, we employ and revise the classic naive Bayes model, for feature fusion and finance prediction. |