174 Hits in 6.4 sec

Developing a supervised learning-based social media business sentiment index

Hyeonseo Lee, Nakyeong Lee, Harim Seo, Min Song
2019 Journal of Supercomputing  
In the first step, after training the sentiment classifiers with several big data sources of social media datasets, we consider three types of feature sets: feature vector, sequence vector and a combination  ...  Also, it shows that the extracted keywords from the sentiment analysis, such as "price," "year-end-tax" and "budget deficit," cause the exchange rates.  ...  Therefore, [14] suggested a collaborative multi-domain sentiment classification approach to simultaneously train sentiment classifiers for multiple domains.  ... 
doi:10.1007/s11227-018-02737-x pmid:32435085 pmcid:PMC7224044 fatcat:ofrn25y6njcvfl2nksvuqoio5a

Multi-channel discourse as an indicator for Bitcoin price and volume movements [article]

Marvin Aron Kennis
2018 arXiv   pre-print
A Granger causality test confirms the predictive causality of the sentiment on the daily percentage price and volume movements, and at the same time underscores the predictive causality of market movements  ...  This makes Bitcoin an interesting subject for such research, as it enables the mapping of sentiment to fundamental events that might otherwise be inaccessible.  ...  This is different from stop word removal, as it is adaptive to domain contexts.  ... 
arXiv:1811.03146v1 fatcat:y2bn7ohccrhf5ppfnvyo6ssiim

The Effects of Twitter Sentiment on Stock Price Returns

Gabriele Ranco, Darko Aleksovski, Guido Caldarelli, Miha Grčar, Igor Mozetič, Tobias Preis
2015 PLoS ONE  
We find a relatively low Pearson correlation and Granger causality between the corresponding time series over the entire time period.  ...  We formalize the procedure by adapting the well-known "event study" from economics and finance to the analysis of Twitter data.  ...  agreement and sentiment classification evaluations.  ... 
doi:10.1371/journal.pone.0138441 pmid:26390434 pmcid:PMC4577113 fatcat:jijdwpeyj5fsjp5mq726gwrj3y

Forecasting Weekly Crude Oil Using Twitter Sentiment of U.S. Foreign Policy and Oil Companies Data

Mourad Oussalah, Ahmed Zaidi
2018 2018 IEEE International Conference on Information Reuse and Integration (IRI)  
The investigation is divided into three parts: 1) a methodology of collecting tweets relevant to US foreign policy and oil companies'; 2) a statistical analysis of the novel features using Granger Causality  ...  Many academics have exploited this wealth of data to extract features including sentiment and word frequency to build reliable forecasting models for financial instruments such as stocks.  ...  ACKNOWLEDGMENT We would like to thank the anonymous reviewers for their valuable suggestions because of which the technical quality of the work presented in this paper has improved.  ... 
doi:10.1109/iri.2018.00037 dblp:conf/iri/OussalahZ18 fatcat:gwlweu27hvhz7fup3lvsq6xvhy

Data science and AI in FinTech: An overview [article]

Longbing Cao, Qiang Yang, Philip S. Yu
2021 arXiv   pre-print
The research on data science and AI in FinTech involves many latest progress made in smart FinTech for BankingTech, TradeTech, LendTech, InsurTech, WealthTech, PayTech, RiskTech, cryptocurrencies, and  ...  -Causality analysis: such as linear and nonlinear Granger causality; causally anomalous multivariate time series; causal tree-based causal inference with instrumental variables; etc.  ...  -Cause-effect: such as evaluating heterogeneous causal effects (e.g., credit for small firms) by causal inference.  ... 
arXiv:2007.12681v2 fatcat:jntzuwaktjg2hmmjypi5lvyht4

Causality Mining in Natural Languages Using Machine and Deep Learning Techniques: A Survey

Wajid Ali, Wanli Zuo, Rahman Ali, Xianglin Zuo, Gohar Rahman
2021 Applied Sciences  
While, decades of development techniques for CM are still prone to performance enhancement, especially for ambiguous and implicitly expressed causalities.  ...  The ineffectiveness of the early attempts is mainly due to small, ambiguous, heterogeneous, and domain-specific datasets constructed by manually linguistic and syntactic rules.  ...  Hence, DL techniques are the best choice by their strong inference ability to deal with implicit and ambiguous causalities.  ... 
doi:10.3390/app112110064 fatcat:btv66da5x5a73auogv5d3lp2bi

Evaluation Methods and Measures for Causal Learning Algorithms [article]

Lu Cheng, Ruocheng Guo, Raha Moraffah, Paras Sheth, K. Selcuk Candan, Huan Liu
2022 arXiv   pre-print
We then examine popular causal inference tools/packages and conclude with primary challenges and opportunities for benchmarking causal learning algorithms in the era of big data.  ...  To bridge from conventional causal inference (i.e., based on statistical methods) to causal learning with big data (i.e., the intersection of causal inference and machine learning), in this survey, we  ...  It is a dataset for binary sentiment classification task. The dataset consists of movie reviews retrieved from the website IMDB 6 .  ... 
arXiv:2202.02896v1 fatcat:ykvg7gfwxfawjgkenvmmkbzpxa

Fusion in stock market prediction: A decade survey on the necessity, recent developments, and potential future directions

Ankit Thakkar, Kinjal Chaudhari
2020 Information Fusion  
We conduct a systematic approach to present a survey for the years 2011-2020 by considering articles that have used fusion techniques for various stock market applications and broadly categorize them into  ...  We also provide an infographic overview of fusion in stock market prediction and extend our survey for other finely addressed financial prediction problems.  ...  Considering that a specific lag period represents strong correlation between the social sentiments and market prices, an SVM-based non-linear granger causality approach was proposed in study [35] .  ... 
doi:10.1016/j.inffus.2020.08.019 pmid:32868979 pmcid:PMC7448965 fatcat:ji7va4kekjh4tgclotgg7na7sa

Data Mining Algorithms for Smart Cities: A Bibliometric Analysis

Anestis Kousis, Christos Tjortjis
2021 Algorithms  
This paper presents a bibliometric analysis to provide a comprehensive overview of studies associated with DM technologies used in smart cities applications.  ...  The bibliometric analysis shows that DM for smart cities is a fast-growing scientific field.  ...  Tse et al. employed the Granger Causality Test (GCT) in their study [42] . GCT is a statistical hypothesis test for determining whether one time series has causal relationships with another.  ... 
doi:10.3390/a14080242 fatcat:zalmt5lwhvaaflxhig44yfuw5i

Semantic Web Mining in Retail Management System using ANN

2019 International journal of recent technology and engineering  
For this review, many sentimental analysis and prediction techniques are observed and compared based on their performance. This survey also focused the dynamic data on the user behaviour.  ...  Based on these considerations, this paper gives detail review about a Semantic web mining based Artificial Neural Network (ANN) for the retail management system.  ...  Granger causality and co integration test were used to predict the Google trends power in the related study statistically.  ... 
doi:10.35940/ijrte.b1439.0982s1119 fatcat:4tyetp4ve5gdfdr5cp6mccw3su

Combining machine-based and econometrics methods for policy analytics insights

Robert J. Kauffman, Kwansoo Kim, Sang-Yong Tom Lee, Ai-Phuong Hoang, Jing Ren
2017 Electronic Commerce Research and Applications  
In fact, the coverage is as broad as for-profit and for-non-profit, private and public, and governmental and non-governmental institutions.  ...  Computational Social Science (CSS) has become a mainstream approach in the empirical study of policy analytics issues in various domains of e-commerce research.  ...  The authors are solely responsible for any errors and omissions.  ... 
doi:10.1016/j.elerap.2017.04.004 fatcat:g6onq7o2yjfpxi5lzofqjhfylm

Modern Views of Machine Learning for Precision Psychiatry [article]

Zhe Sage Chen, Prathamesh Kulkarni, Isaac R. Galatzer-Levy, Benedetta Bigio, Carla Nasca, Yu Zhang
2022 arXiv   pre-print
Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health.  ...  Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment.  ...  We thank Robert MacKay for English proofreading.  ... 
arXiv:2204.01607v1 fatcat:ctn65gxiijc4npyj3sxl4jxlzy

Reverse-engineering biological networks from large data sets [article]

Joseph L. Natale, David Hofmann, Damian G. Hernández, Ilya Nemenman
2017 arXiv   pre-print
Many of these predictions have clinical relevance, suggesting novel paradigms for drug discovery and disease treatment.  ...  We first summarize several key application areas in which inferred networks have made successful predictions.  ...  However, a method due to Granger [250] combines autoregression with the aforementioned notion of temporal precedence to infer quantify a robust stand-in for causality -namely, Weiners predictability  ... 
arXiv:1705.06370v2 fatcat:owto6kvzizbebggfagrrf7itsi

Twitter User Representation Using Weakly Supervised Graph Embedding [article]

Tunazzina Islam, Dan Goldwasser
2022 arXiv   pre-print
While we focus on lifestyle-related tweets (i.e., yoga, keto), our method for constructing user representation readily generalizes to other domains.  ...  In this paper, we propose a weakly supervised graph embedding based framework for understanding user types.  ...  Acknowledgments We gratefully acknowledge Md Masudur Rahman and the anonymous reviewers for their insightful comments. We further thank our annotators.  ... 
arXiv:2108.08988v3 fatcat:twwzp2d435h2zdidwkddjrh2he

Reverse-Engineering Biological Networks From Large Data Sets [article]

Joseph Lane Natale, David Hofmann, Damián G. Hernández, Ilya Nemenman
2017 bioRxiv   pre-print
Many of these predictions have clinical relevance, suggesting novel paradigms for drug discovery and disease treatment.  ...  We first summarize several key application areas in which inferred networks have made successful predictions.  ...  However, a method due to Granger [250] combines autoregression with the aforementioned notion of temporal precedence to infer quantify a robust stand-in for causality -namely, Weiners predictability  ... 
doi:10.1101/142034 fatcat:b4aowavcwfd3hnob4e6uu2yhsi
« Previous Showing results 1 — 15 out of 174 results