Going Back in Time to Predict the Future - The Complex Role of the Data Collection Period in Social Media Analytics

2020 | Information Systems Frontiers | Citations: 0

Authors: Stieglitz, Stefan; Meske, Christian; Ross, Björn; Mirbabaie, Milad

Abstract: In the context of events that involve public voting, such as televised competiti ... Expand

Abstract: In the context of events that involve public voting, such as televised competitions or elections, it has increasingly been recognized that communication data from social media is related to the outcome. Existing studies mainly analyse the number of messages and their sentiment, yet the role of different data collection periods has not been examined sufficiently. We collected Twitter data in 2015 and 2016 to examine the relationship between the audience voting of the Eurovision Song Contest and predictors based on quantity and emotions, and compared the results of using data from before and during the event. We found that the choice of time period greatly affected the results obtained. Data collected prior to the event exhibited a much stronger association with the final ranking than data collected during the event. In addition, the model based on pre-event data in 2015 showed considerable accuracy in predicting the 2016 results, illustrating the usefulness of social media data for predicting the outcomes of events outside social media. Collapse

Topics: Twitter social media logistics management evaluation criteria

Methods: sentiment analysis descriptive statistic machine learning regression analysis method logistic regression

Cryptocurrency price prediction based on multiple market sentiment

2020 | HICSS | Citations: 0

Authors: Wang, Yu; Chen, Runyu

Abstract: With the rapid development of the Internet, cryptocurrencies have been gaining i ... Expand

Abstract: With the rapid development of the Internet, cryptocurrencies have been gaining increasing amounts of attention dramatically. As a digital currency, it is not only used worldwide for online payments, but also traded as an investment tool on the market. Therefore, the ability to predict the price volatility will facilitate future investment and payment decisions. However, there are many uncertainties in the price movement of cryptocurrencies, and the prediction is extremely difficult. Collapse

Topics: cryptocurrency social media Tether Ethereum Bitcoin

Methods: computational algorithm experiment deep learning support vector machine machine learning

Noise Trader Behavior - A Disaggregated Approach to Understanding News Reception in Financial Markets

2018 | European Conference On Information Systems | Citations: 0

Authors: Hannemann, Felix; PrÃ, Nicolas

Abstract: Financial disclosures serve as primary intermediaries between companies and inve ... Expand

Abstract: Financial disclosures serve as primary intermediaries between companies and investors. However, investors have different information processing skills and might easily be misled by noisy signals that lack a deeper meaning. In financial markets, this is formalized by the noise trader theory, which groups investors into two categories: (a) informed investors assumed to form rational decisions and (b) noise traders forming beliefs partly based on non-fundamental noise signals and news sentiment. Yet, little is known about how these groups actually interpret textual information in financial statements and how the resulting stock market reaction differs. This work extends previous research by unraveling the role of word choice and semantic orientation in financial disclosures for both investor types. For this purpose, we use Kalman filtering to decompose the stock market reaction following the publication of U.S. regulated Form 8-K filings into a fundamental price component and a noise residual. We then use LASSO regression to identify the statistically relevant words for informed investors and noise traders. According to our results, each investor type assigns significantly different interpretations and degrees of importance to individual words and documents. Collapse

Topics: decision making data breach website

Methods: lasso regression descriptive statistic sentiment analysis statistical hypothesis test longitudinal research

E-Business Value in Small and Medium-Sized Enterprises in Southern Africa: A Quantitative Content Analysis of Websites

2018 | Americas Conference on Information Systems | Citations: 0

Authors: Tsumake, Meduduetso; Kyobe, Michael

Abstract: E-business models adopted by SMEs are often abstruse and poorly represented, whi ... Expand

Abstract: E-business models adopted by SMEs are often abstruse and poorly represented, which makes them difficult to evaluate e-business value. This research drew from different theories to create a comprehensive model for e-business evaluation. The study adopted Gerbner’s theory of communication exchange which posits that by studying the events of the communication exchange, one can infer about the state of the systems engaged in the exchange and their relationships. Consequently quantitative website content analysis of 20 SMEs was conducted to determine their e-business value. The results revealed that most products and services are offered and traded by an SME led by an entrepreneur who demonstrates commitment to the business and is visionary. Also, when there is more technology functionality within the business and its network, connections with other actors are enabled which instigates communication. Lastly, value activity is created when e-business is well maintained and used by employees with intellectual resources. Collapse

Topics: electronic business website value creation strategic management business process management

Methods: conceptual modelling parametric test Student's t-test qualitative content analysis descriptive statistic

Theories: communication theory

A hybrid approach by integrating wavelet-based feature extraction with MARS and SVR for stock index forecasting

2013 | Decision Support Systems | Citations: 0

Authors: Kao, Ling-Jing; Chiu, Chih-Chou; Lu, Chi-Jie; Chang, Chih-Hsiang

Abstract: Forecasting stock prices is a major activity of financial firms and private inve ... Expand

Abstract: Forecasting stock prices is a major activity of financial firms and private investors when they make investment decisions. Feature extraction is usually the first step of a stock price forecasting model development. Wavelet transform, used mainly for the extraction of information contained in signals, is a signal processing technique that can simultaneously analyze the time domain and the frequency domain. When wavelet transform is employed to construct a forecasting model, the wavelet basis functions and decomposition stages need to be determined first. However, because forecasting models constructed by different wavelet sub-series would exhibit different forecasting capabilities and yield varying forecast results, the selection of wavelet that can lead to an optimal forecast outcome is extremely critical in model construction. In this study, a new stock price forecasting model which integrates wavelet transform, multivariate adaptive regression splines (MARS), and support vector regression (SVR) (called Wavelet-MARS-SVR) is proposed to not only address the problem of wavelet sub-series selection but also improve the forecast accuracy. The performance of the proposed method is evaluated by comparing the forecasting results of Wavelet-MARS-SVR with the ones made by other five competing approaches (Wavelet-SVR, Wavelet-MARS, single ARIMA, single SVR and single ANFIS) on the stock price data of two newly emerging stock markets and two mature stock markets. The empirical study shows that the proposed approach can not only solve the problem of wavelet sub-series selection but also outperform other competing models. Moreover, according to the sub-series which are selected by the proposed approach, we can successfully identify the data of which sessions (or points in time) among past stock market prices exerted significant impact on the construction of the forecasting model. Collapse

Topics: decision making

Methods: autoregressive integrated moving average nonparametric test longitudinal research time series analysis Wilcoxon signed-rank test

Financial time series forecasting using independent component analysis and support vector regression

2009 | Decision Support Systems | Citations: 19

Authors: Lu, Chi-Jie; Lee, Tian-Shyug; Chiu, Chih-Chou

Abstract: As financial time series are inherently noisy and non-stationary, it is regarded ... Expand

Abstract: As financial time series are inherently noisy and non-stationary, it is regarded as one of the most challenging applications of time series forecasting. Due to the advantages of generalization capability in obtaining a unique solution, support vector regression (SVR) has also been successfully applied in financial time series forecasting. In the modeling of financial time series using SVR, one of the key problems is the inherent high noise. Thus, detecting and removing the noise are important but difficult tasks when building an SVR forecasting model. To alleviate the influence of noise, a two-stage modeling approach using independent component analysis (ICA) and support vector regression is proposed in financial time series forecasting. ICA is a novel statistical signal processing technique that was originally proposed to find the latent source signals from observed mixture signals without having any prior knowledge of the mixing mechanism. The proposed approach first uses ICA to the forecasting variables for generating the independent components (ICs). After identifying and removing the ICs containing the noise, the rest of the ICs are then used to reconstruct the forecasting variables which contain less noise and served as the input variables of the SVR forecasting model. In order to evaluate the performance of the proposed approach, the Nikkei 225 opening index and TAIEX closing index are used as illustrative examples. Experimental results show that the proposed model outperforms the SVR model with non-filtered forecasting variables and a random walk model. Collapse

Methods: time series analysis longitudinal research experiment computational algorithm support vector machine

Understanding and attenuating decision bias in the use of model advice and other relevant information

2006 | Decision Support Systems | Citations: 8

Authors: Jones, Donald R.; Wheeler, Patrick; Appan, Radha; Saleem, Naveed

Abstract: A human judge faced with model advice, modeled information (used by the model to ... Expand

Abstract: A human judge faced with model advice, modeled information (used by the model to compute the advice), and unmodeled information (known by the human but not included in the model) should use a “divide-and-conquer” strategy in which the human judge relies completely on the model to process the modeled information and focuses all energy on assessing and adjusting for the unmodeled information [D.R. Jones, D. Brown, The division of labor between human and computer in the Presence of Decision Support System Advice, Decision Support Systems 33 (2002) 375–388]. This paper extends Jones and Brown [D.R. Jones, D. Brown, The division of labor between human and computer in the Presence of Decision Support System Advice, Decision Support Systems 33 (2002) 375–388] in two studies. In Study 1, we find that, in lieu of the divide-and-conquer strategy, human judges give weight to all three types of inputs and that giving weight to the modeled information degrades performance. In Study 2, we find that (1) as strategies approach the divide-and-conquer strategy judgment performance improves, and (2) the divide-and-conquer strategy can be encouraged by a combination of instruction and a decision support feature. Application of these results could improve judgment in a variety of important contexts. Collapse

Topics: decision support system database system decision support decision making accounting

Methods: experiment descriptive statistic parametric test ANOVA post-hoc analysis

The Accuracy of Post-Negotiation Estimates of the Other Negotiator's Payoff

2004 | Group Decision and Negotiation | Citations: 0

Authors: Mumpower, Jeryl L.; Sheffield, Jim; Darling, Thomas A.; Milter, Richard G.

Abstract: This paper describes two empirical studies of interpersonal understanding in neg ... Expand

Abstract: This paper describes two empirical studies of interpersonal understanding in negotiations. In the first study, the accuracy of post-negotiation estimates of the other negotiator's payoff was assessed after a role-playing simulation. Only a minority of participants exhibited evidence of the fixed pie bias, in which negotiators view all negotiations as distributive, fixed-sum situations. Participants' estimates of the other negotiator's payoff were generally better fit by the equal payoffs model, which presumes that participants believe the other negotiator's payoff is the same as one's own. This held true for both distributive task structures in which the fixed-pie view is descriptively appropriate and integrative negotiation task structures in which the fixed-pied view is inaccurate. The results did not support the hypothesis that superior understanding about the other negotiator's interests helps negotiators to achieve better outcomes for themselves; the correlation between predictive accuracy and the value of participants' own payoffs was generally low. Collapse

Topics: task structure

Methods: machine learning descriptive statistic ANOVA parametric test chi squared test

A decision support tool for allocating hospital bed resources and determining required acuity of care

2003 | Decision Support Systems | Citations: 8

Authors: Walczak, Steven; Pofahl, Walter E.; Scorpio, Ronald J.

Abstract: Limitations in health care funding require physicians and hospitals to find effe ... Expand

Abstract: Limitations in health care funding require physicians and hospitals to find effective ways to utilize resources. Neural networks provide a method for predicting resource utilization of costly resources used for prolonged periods of time. Injury severity knowledge is used to determine the acuity of care required for each patient and length of stay is used to determine duration of inpatient hospitalization. Neural networks perform well on these medical domain problems, predicting total length of stay within 3 days for pediatric trauma (population mean and S.D. 4.37±45.12) and within 4 days for acute pancreatitis patients (7.75±79.19). Collapse

Topics: decision support missing data decision support system electronic health record database system

Methods: artificial neural network descriptive statistic simulation supervised learning Student's t-test

Supply chain reengineering using a core process analysis matrix and object-oriented simulation

2002 | Information & Management | Citations: 0

Authors: Changchien, S. Wesley; Shen, Hsiao-Yun

Abstract: To satisfy and respond quickly to customers’ demand, many companies are now aggr ... Expand

Abstract: To satisfy and respond quickly to customers’ demand, many companies are now aggressively focusing on supply chain management in order to strengthen their competitiveness. This paper proposes an integrated business process reengineering (BPR) framework for improving performance. There are several steps in this framework: creating vision, identifying core processes to be redesigned, analyzing current core processes, designing for innovation, evaluating the new processes, selecting the best, and transforming and implementing the resulting design. A core process analysis matrix is proposed for identifying the critical processes. System simulation is useful in measuring the performance and predicting the effect of change on the system. To reduce the risk of BPR, an object-oriented simulation framework is developed for evaluating and analyzing the reengineering proposals. This paper uses a case study to show the value of the method. Collapse

Topics: supply chain management marketing management business process management business process re-engineering

Methods: case study Bayesian analysis descriptive statistic activity diagram simulation