scholarly journals How to gauge investor behavior? A comparison of online investor sentiment measures

2021 ◽  
Author(s):  
Daniele Ballinari ◽  
Simon Behrendt
Keyword(s):  
Machine Learning ◽  
Abnormal Returns ◽  
Investor Sentiment ◽  
Investor Behavior ◽  
Learning Approaches ◽  
Financial Applications ◽  
Model Free ◽  
Retail Investors ◽  
Regression Framework ◽  
Social Media Platforms

AbstractGiven the increasing interest in and the growing number of publicly available methods to estimate investor sentiment from social media platforms, researchers and practitioners alike are facing one crucial question – which is best to gauge investor sentiment? We compare the performance of daily investor sentiment measures estimated from Twitter and StockTwits short messages by publicly available dictionary and machine learning based methods for a large sample of stocks. To determine their relevance for financial applications, these investor sentiment measures are compared by their effects on the cross-section of stocks (i) within a Fama and MacBeth (J Polit Econ 81:607–636, 1973) regression framework applied to a measure of retail investors’ order imbalances and (ii) by their ability to forecast abnormal returns in a model-free portfolio sorting exercise. Interestingly, we find that investor sentiment measures based on finance-specific dictionaries do not only have a greater impact on retail investors’ order imbalances than measures based on machine learning approaches, but also perform very well compared to the latter in our asset pricing application.

scholarly journals Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity

2018 ◽  
Vol 15 (9) ◽  
pp. 1881 ◽  
Author(s):  
Sina Keller ◽  
Philipp Maier ◽  
Felix Riese ◽  
Stefan Norra ◽  
Andreas Holbach ◽  
...  
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Chlorophyll A ◽  
Green Algae ◽  
Hyperspectral Data ◽  
Coefficient Of Determination ◽  
Inland Waters ◽  
Learning Approaches ◽  
River Elbe ◽  
Regression Framework

Inland waters are of great importance for scientists as well as authorities since they are essential ecosystems and well known for their biodiversity. When monitoring their respective water quality, in situ measurements of water quality parameters are spatially limited, costly and time-consuming. In this paper, we propose a combination of hyperspectral data and machine learning methods to estimate and therefore to monitor different parameters for water quality. In contrast to commonly-applied techniques such as band ratios, this approach is data-driven and does not rely on any domain knowledge. We focus on CDOM, chlorophyll a and turbidity as well as the concentrations of the two algae types, diatoms and green algae. In order to investigate the potential of our proposal, we rely on measured data, which we sampled with three different sensors on the river Elbe in Germany from 24 June–12 July 2017. The measurement setup with two probe sensors and a hyperspectral sensor is described in detail. To estimate the five mentioned variables, we present an appropriate regression framework involving ten machine learning models and two preprocessing methods. This allows the regression performance of each model and variable to be evaluated. The best performing model for each variable results in a coefficient of determination R 2 in the range of 89.9% to 94.6%. That clearly reveals the potential of the machine learning approaches with hyperspectral data. In further investigations, we focus on the generalization of the regression framework to prepare its application to different types of inland waters.

scholarly journals Influence of Bloomberg’s Investor Sentiment Index: Evidence from European Union Financial Sector

Mathematics ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 297
Author(s):  
Mariano González-Sánchez ◽  
M. Encina Morales de Vega
Keyword(s):  
European Union ◽  
Financial Services ◽  
Abnormal Returns ◽  
Investor Sentiment ◽  
Daily Basis ◽  
Investor Behavior ◽  
Pricing Model ◽  
Asset Pricing Model ◽  
Type Process ◽  
Standardized Residuals

A part of the financial literature has attempted to explain idiosyncratic asset shocks through investor behavior in response to company news and events. As a result, there has been an increase in the development of different investor sentiment measurements. This paper analyses whether the Bloomberg investor sentiment index has a causal relationship with the abnormal returns and volume shocks of major European Union (EU) financial companies through a sample of 85 financial institutions over 4 years (2014–2018) on a daily basis. The i.i.d. shocks are obtained from a factorial asset pricing model and ARMA-GARCH-type process; then we checked whether there is both individual and joint causality between the standardized residuals. The results show that the explanatory capacity of the shocks of the firm Bloomberg sentiment index is low, although there is empirical evidence that the effects correspond more to the situation of the financial subsector (banks, real estate, financial services and insurance) than to the company itself, with which we conclude that the sentiment index analyzed reflects a sectorial effect more than individual one.

scholarly journals Rumour Detection Models & Tools for Social Networking Sites

2019 ◽  
Vol 9 (2) ◽  
pp. 3291-3296
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Social Networking ◽  
Social Networking Sites ◽  
Early Stage ◽  
Economic Losses ◽  
Learning Approaches ◽  
The People ◽  
Social Media Platforms ◽  
Fuzzy Logic Technique

Efficient utilization of social networking sites (SNS) had reduced communication delays, at the same time increased rumour messages. Subsequently, mischievous people started sharing of rumours via social networking sites for gaining personal benefits. This falsified information (i.e., rumour) creates misconception among the people of society influencing socio-economic losses by disrupting the routine businesses of private and government sectors. Communication of rumour information requires rigorous surveillance, before they become viral through social media platforms. Detecting these rumour words in an early stage from messaging applications needs to be predicted using robust Rumour Detection Models (RDM) and succinct tools. RDM are effectively used in detecting the rumours from social media platforms (Twitter, Linkedln, Instagram, WhatsApp, Weibo sena and others) with the help of bag of words and machine learning approaches to a limited extent. RDM fails in detecting the emerging rumours that contains linguistic words of a specific language during the chatting session. This survey compares the various RDM strategies and Tools that were proposed earlier for identifying the rumour words in social media platforms. It is found that many of earlier RDM make use of Deep learning approaches, Machine learning, Artificial Intelligence, Fuzzy logic technique, Graph theory and Data mining techniques. Finally, an improved RDM model is proposed in Figure 2, efficiency of this proposed RDM models is improved by embedding of Pre-defined rumour rules, WordNet Ontology and NLP/machine learning approach giving the precision rate of 83.33% when compared with other state-of-art systems.

scholarly journals Deep Learning-Based Election Results Prediction Using Twitter Activity

2021 ◽  
Author(s):  
Haider Ali ◽  
Haleem Farman ◽  
Hikmat Yar ◽  
Zahid Khan ◽  
Shabana Habib ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
General Election ◽  
Learning Approaches ◽  
Social Media Platforms ◽  
General Elections ◽  
Election Results ◽  
Twitter Activity ◽  
The Stability

Abstract Nowadays, political parties have widely adopted social media for their party promotions and election campaigns. During the election, Twitter and other social media platforms are used for political coverage to promote the party and its candidates. This research discusses and estimates the stability of many volumetric social media approaches to forecast election results from social media activities. Numerous machine learning approaches are applied to opinions shared on social media for predicting election results. This paper presents a machine learning model based on sentiment analysis to predict Pakistan's general election results. In a general election, voters vote for their favorite party or candidate based on their personal interests. Social media has been extensively used for the campaign in Pakistan general election 2018. Using a machine learning technique, we provide a five-step process to analyze the overall election results, whether fair or unfair. The work is concluded with detailed experimental results and a discussion on the outcomes of sentiment analysis for real-world forecasting and approval for general elections in Pakistan.

scholarly journals EFFECTS OF THE PRE-REPURCHASE SYSTEMATIC RISK ON THE RELATIONSHIP BETWEEN INVESTOR BEHAVIOR, MARKET FACTORS AND THE STOCK PRICE RESPONSES

2018 ◽  
Vol 19 (4) ◽  
pp. 673-705
Author(s):  
Ying-Sing Liu
Keyword(s):  
Stock Price ◽  
Abnormal Returns ◽  
Investor Sentiment ◽  
Systematic Risk ◽  
Investor Behavior ◽  
Open Market ◽  
Short Term ◽  
Price Response ◽  
Market Factors ◽  
The Relationship

This study explores the pre-repurchase systematic risk will affect the abnormal returns in the open-market repurchase event period and also change the relationship between the investor sentiment, trading activity, market factors and stock price response during the event on Taiwan stock market. Based on threshold regression models, it is found that the pre-repurchase systematic risk will significantly change the relationship between investor behavior, market factors and stock price responses and the asymmetry of the relationship exists when pre-repurchase systematic risk is lower than a repartition, which supports that institutional investors and credit trading investors differ in these existing relationships. When the pre-repurchase beta is below repartition, it will be detrimental to the returns in event period. But on the contrary, the returns in the short-term shock of news exposure period present the favorable results, which may be related to the fact that there exists sentiment premium in short-term when credit trading investors’ repurchase news exposure occurs. Finally, the study is to confirm the effect of systematic risk for returns and investor sentiment, these results have not been further explored in the past, and can be used as the firm’s evalu-ation reference to the repurchase program in the future.

Analysis of Machine Learning Approaches for Sentiment Analysis of Twitter Data

2020 ◽  
Vol 17 (9) ◽  
pp. 4535-4542
Author(s):  
Ramneet ◽  
Deepali Gupta ◽  
Mani Madhukar
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Analysis Data ◽  
Research Area ◽  
Machine Learning Algorithms ◽  
Product Reviews ◽  
Learning Approaches ◽  
Social Media Platforms ◽  
Film Reviews

For the past few years, sentiment analysis has been growing rapidly and with the abundance of computation power and plethora of machine learning algorithms, sentiment analysis has found numerous applications and acceptance as research area in machine learning. This paper covers analysis of sentiment analysis dealing with different aspects of its applications such as customer reviews, product reviews, film reviews, emotion detection, market research or many more such areas. To conduct sentiment analysis, data is extracted from various social media platforms like Twitter, Facebook etc. The data available on these social media platforms is primarily unstructured, therefore to analyze this data it must be pre-processed, feature vector identified and further implementation of models to trained and tested on different algorithms. There are several algorithms such as SVM, Naïve Bayes, K-means, KNN, decision tree, random forest and other algorithms, which are used to evaluate and hybrid to improve the efficiency and accuracy of the model.

scholarly journals Machine Learning in Model-free Mechanical Property Imaging: Novel Integration of Physics With the Constrained Optimization Process

2021 ◽  
Vol 9 ◽  
Author(s):  
Cameron Hoerig ◽  
Jamshid Ghaboussi ◽  
Yiliang Wang ◽  
Michael F. Insana
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Measurement Data ◽  
Optimization Methods ◽  
Patient Specific ◽  
Learning Approaches ◽  
Element Analysis ◽  
Physical Constraints ◽  
Model Free ◽  
Force Displacement

The Autoprogressive Method (AutoP) is a fundamentally different approach to solving the inverse problem in quasi-static ultrasonic elastography (QUSE). By exploiting the nonlinear adaptability of artificial neural networks and physical constraints imposed through finite element analysis, AutoP is able to build patient specific soft-computational material models from a relatively sparse set of force-displacement measurement data. Physics-guided, data-driven models offer a new path to the discovery of mechanical properties most effective for diagnostic imaging. AutoP was originally applied to modeling mechanical properties of materials in geotechnical and civil engineering applications. The method was later adapted to reconstructing maps of linear-elastic material properties for cancer imaging applications. Previous articles describing AutoP focused on high-level concepts to explain the mechanisms driving the training process. In this review, we focus on AutoP as applied to QUSE to present a more thorough explanation of the ways in which the method fundamentally differs from classic model-based and other machine learning approaches. We build intuition for the method through analogy to conventional optimization methods and explore how maps of stresses and strains are extracted from force-displacement measurements in a model-free way. In addition, we discuss a physics-based regularization term unique to AutoP that illuminates the comparison to typical optimization procedures. The insights gained from our hybrid inverse method will hopefully inspire others to explore combinations of rigorous mathematical techniques and conservation principles with the power of machine learning to solve difficult inverse problems.

Sign in / Sign up

Export Citation Format

Share Document