Yahoo! for Amazon: Sentiment Extraction from Small Talk on the Web
Management SciencePublished 1 September 2007
Sanjiv Ranjan Das, Mike Y. Chen
Citations1,442
SJR quartileQ1
SJR score5.72
SNIP2.88
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A methodology for extracting small investor sentiment from stock message boards is developed, which comprises different classifier algorithms coupled together by a voting scheme.
Abstract
Extracting sentiment from text is a hard semantic problem. We develop a methodology for extracting small investor sentiment from stock message boards. The algorithm comprises different classifier algorithms coupled together by a voting scheme. Accuracy levels are similar to widely used Bayes classifiers, but false positives are lower and sentiment accuracy higher. Time series and cross-sectional aggregation of message information improves the quality of the resultant sentiment index, particularly in the presence of slang and ambiguity. Empirical applications evidence a relationship with stock values—tech-sector postings are related to stock index levels, and to volumes and volatility. The algorithms may be used to assess the impact on investor opinion of management announcements, press releases, third-party news, and regulatory changes.
Keywords
Computer ScienceDecision SciencesEconomics, Econometrics and Finance
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Statistics and ComputingA tutorial on support vector regression
13,005 Citations2004Alex Smola, Bernhard Schölkopf
This tutorial gives an overview of the basic ideas underlying Support Vector (SV) machines for function estimation, and includes a summary of currently used algorithms for training SV machines, covering both the quadratic programming part and advanced methods for dealing with large datasets.
Thumbs up?
6,987 Citations2002Bo Pang, Lillian Lee +1 more
This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
International Conference on Neural Information ProcessingAdvances in kernel methods: support vector learning
5,815 Citations1999Bernhard Schölkopf, Christopher J. C. Burges +1 more
Support vector machines for dynamic reconstruction of a chaotic system, Klaus-Robert Muller et al pairwise classification and support vector machines, Ulrich Kressel.
The Journal of FinanceGiving Content to Investor Sentiment: The Role of Media in the Stock Market
4,505 Citations2007Paul C. Tetlock
A circuit for the electrical system of an automotive vehicle, such as a truck, interfaces a brake switch, a combination turn signal/hazard warning signal switch, and an engine electronic control module (ECM) that has two separate brake signal inputs.
Lecture notes in statisticsBayesian Learning for Neural Networks
4,375 Citations1996Radford M. Neal
Bayesian Learning for Neural Networks shows that Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional neural network learning methods.
Technical reportsMaking Large-Scale SVM Learning Practical
4,317 Citations2006Thorsten Joachims
This chapter presents algorithmic and computational results developed for SVM light V 2.0, which make large-scale SVM training more practical and give guidelines for the application of SVMs to large domains.
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
3,175 Citations2015Vladimir Vapnik, Alexey Chervonenkis
This chapter reproduces the English translation by B. Seckler of the paper by Vapnik and Chervonenkis in which they gave proofs for the innovative results they had obtained in a draft form in July 1966 and announced in 1968 in their note in Soviet Mathematics Doklady.
Marketing ScienceUsing Online Conversations to Study Word-of-Mouth Communication
2,607 Citations2004David Godes, Dina Mayzlin
It is found that online conversations may offer an easy and cost-effective opportunity to measure word of mouth and it is shown that a measure of the dispersion of conversations across communities has explanatory power in a dynamic model of TV ratings.
The Journal of FinanceIs All That Talk Just Noise? The Information Content of Internet Stock Message Boards
2,400 Citations2004Werner Antweiler, Murray Z. Frank
Review of Financial StudiesWhen Are Contrarian Profits Due to Stock Market Overreaction?
1,787 Citations1990Andrew W. Lo, A. Craig MacKinlay
Hierarchically Classifying Documents Using Very Few Words
840 Citations1997Daphne Koller, Mehran Sahami
This work proposes an approach that utilizes the hierarchical topic structure to decompose the classification task into a set of simpler problems, one at each node in the classification tree, which can be solved accurately by focusing only on a very small set of features, those relevant to the task at hand.
Enhanced hypertext categorization using hyperlinks
775 Citations1998Soumen Chakrabarti, Byron Dom +1 more
This work has developed a text classifier that misclassified only 13% of the documents in the well-known Reuters benchmark; this was comparable to the best results ever obtained and its technique also adapts gracefully to the fraction of neighboring documents having known topics.
SSRN Electronic JournalMore than Words: Quantifying Language to Measure Firms' Fundamentals
560 Citations2007Paul C. Tetlock, Maytal Saar‐Tsechansky +1 more
Financial Analysts JournalNews or Noise? Internet Postings and Stock Prices
402 Citations2001Robert Tumarkin, Robert Whitelaw
The VLDB JournalScalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomies
230 Citations1998Soumen Chakrabarti, Byron Dom +2 more
An automatic system that starts with a small sample of the corpus in which topics have been assigned by hand, and then updates the database with new documents as the corpus grows, assigning topics to these new documents with high speed and accuracy is described.
SSRN Electronic JournalCheap Talk on the Web: The Determinants of Postings on Stock Message Boards
201 Citations1999Peter D. Wysocki
Journal of Financial EconomicsHow does the Internet affect trading? Evidence from investor behavior in 401(k) plans
161 Citations2002James J. Choi
Journal of Accounting and EconomicsWhisper forecasts of quarterly earnings per share
152 Citations1999Mark Bagnoli, Messod D. Beneish +1 more
The VLDB JournalFast and accurate text classification via multiple linear discriminant projections
140 Citations2003Soumen Chakrabarti, Shourya Roy +1 more
SIMPL is presented, a nearly linear-time classification algorithm that mimics the strengths of SVMs while avoiding the training bottleneck and not only approaches and sometimes exceeds SVM accuracy, but also beats the running time of a popular SVM implementation by orders of magnitude.
Financial ManagementeInformation: A Clinical Study of Investor Discussion and Sentiment
121 Citations2005Sanjiv Ranjan Das, Asís Martínez-Jerez +1 more
This intensive clinical study of on-line discussions suggests mechanisms individual investors and groups can use to analyze and digest company information and analyzes the determinants of sentiment and disagreement.
RePEc: Research Papers in EconomicsSoft information in earnings announcements: news or noise?
92 Citations2008Elizabeth Demers, Clara Vega
The Journal of InvestingThree Hundred Years of Stock Market Manipulations
48 Citations2001David Leinweber, Ananth Madhavan
The new technology of market manipulation in a historical context is placed, a number of remarkable manipulations are reviewed, and the basis for strategies needed in modern markets are suggested.
National Bureau of Economic ResearchDoes the Internet Increase Trading? Evidence from Investor Behavior in 401(k) Plans
31 Citations2000James J. Choi, David Laibson +1 more
Elsevier eBooksCONCEPTUAL DEPENDENCY THEORY
31 Citations1975Roger C. Schank
This chapter explains by means of examples and discussion to demonstrate how one can know what the best representation for a sentence is.
SSRN Electronic JournalNoisytalk.com: Broadcasting Opinions in a Noisy Environment
14 Citations2001Anat R. Admati, Paul Pfleiderer
A model where an altruistic sender, who may or may not be informed, broadcasts one of a finite set of messages to rational receivers shows that overconfidence can improve informativeness when broadcasting is costly.
Internet Stock Message Boards and Stock Returns
12 Citations2002Werner Antweiler, Murray Z. Frank