1. Predicting Market Movements: From Breaking News to Emerging Social Media
Dr. Hsinchun Chen
Director, Artificial Intelligence Lab
University of Arizona
Acknowledgements: NSF CRI; NSF EXP-LA; DOD DTRA, CTFP, NPS; (ARFL WMD, CIA, FBI)

2. PREDICITNG MARKET MOVEMENTS

3. Predicting Markets
Markets: international markets, emerging markets, import/export markets, financial market, stock market, commodity market, retail market
Economics (macro), international relations (trade, geopolitics), finance (international/banking/stock), accounting (market return), marketing (sales/retailing)
US (NSF SBE, social behavioral economics; governments, think tanks), Europe/Asia  Business school research in not science (cannot be funded by NSF in US)!
Economics, finance, accounting, political science, social science, marketing, computer science (small, no funding in US!), MIS (business intelligence)
Geopolitical/econ/finance/accounting models/theories, market metrics/parameters, analytical techniques, results interpretations, predicating markets
EMH (efficiency market hypothesis), RWT (random walk theory), CAPM (capital asset pricing model), quant/algorithm trading

4. Research Opportunities
Sophisticated econ/finance/accounting/marketing models/theories, established analytical techniques and metrics (numeric), abundant structured databases (financial metrics, economic indicators, stock quotes)
New, diverse unstructured (text) web-enabled business data sources, e.g., 10K/10Q SEC reports, mass media news, local news, Internet news, financial blogs, investor forums, tweets…
Topic extraction, named entity recognition, sentiment/affect analysis, multilingual language models, social network analysis, statistical machine learning, temporal data/text mining, time-series analysis…

5. Nerds on Wall Street
“Future technological stars…(1) Advanced electronic market tools; (2) Understanding both quantitative and qualitative information…”
“The Text Frontier, Collective Intelligence, Social Media, and Market Monitors”
“Stocks are stories, bonds are mathematics.”
David Leinweber, 2009

6. BUSINESS MASS MEDIA, SOCIAL MEDIA,
AZ BIZ INTEL:
BUSINESS MASS MEDIA, SOCIAL MEDIA,
TEXT ANALYTICS, SENTIMENT ANALYSIS, SPIKE DETECTION, FINANCE/ACCOUNTING/MARKETING MODELING, PREDICTING MARKET MOVEMENTS

7. Business Intelligence & Analytics
$3B BI revenue in 2009 (Gartner, 2006)
The Data Deluge (The Economists, March 2010); internet traffic 667 Exabytes by 2013, Cisco; Total amount of information in 2010, 1.2 Zettabyte (KB-MB-GB-TB-PB-EB-ZB-YB)
$9.4B BI software M&A spending in 2010 and $14.1B by 2014 (Forrester)
IBM spent $14B in BI in five years; $9B BI revenue in 2010 (USA Today, November 2010); 24 acquisitions, 10,000 BI software developers, 8,000 BI consultants, 200 BI mathematicians  Acquired i2/COPLINK in 2011

8. Business Intelligence & Analytics
BI: “skills, technologies, applications, and practices used to help an enterprise better understand its business and market.”
Technologies: data warehousing; Extraction, Transformation, and Load(ETL); Business Performance Management (BPM); visual dashboards; and advanced knowledge discovery using data and text mining
BI 2.0: web intelligence, web analytics, web 2.0, social media analytics, opinion mining; cloud computing and web services; real-time monitoring and mining; enterprise performances (marketing/accounting/finance/healthcare)

9. AZ BIZ INTEL Mass media, social media contents
Text & social media analytics techniques
Finance/accounting/marketing models (Tetlock/Columbia, Antweiler/UBC, Das/Santa Clara)  NYU (Dhar), Arizona (Dhaliwal, Kelly, Jiang, Lusch, Yong), National Taiwan U (Li, Hong, Lu)
Bag of words, named entities, proper nouns, topics (1, 2-, 3- grams)
Sentiment/valence, lexicons, machine learning, stakeholder analysis, EFLS analysis
Time series models, spike detection, decaying function, trading windows, targeted sentiment
Econometrics/regression models (R-sqr, p-value), 10-fold validation (F, accuracy), simulated trading (cost, frequency, exit)

10. AZ ONLINE WOM

11. AZ WOM: events, volume, sentiment

12. Results Evolution of online WOM through new-product lifecycle
WOM communication starts early in preproduction, becomes highly active before movie release, then diminishes gradually
Valence has a clear decreasing trend over time, indicating that WOM becomes more negative after movie release
Subjectivity, number of sentences and number of valence words stay stable over time

13. IT’S THE BUZZ!

14. AZ STOCK TRACKER I & II

15. Literature Review: Stock Performance Prediction
Theoretical perspectives on stock behavior
Efficient market hypothesis (Fama 1964)
Price of a stock reflects all available information
Market reacts instantaneously; impossible to outperform
Random walk theory (Malkiel 1973)
Price of a stock varies randomly over time
Future prediction, outperforming the market is impossible
Pessimistic assessments of the predictability of stock behavior refuted through empirical studies
Lo and MacKinlay 1988; Jaffe et al 1989; Pesaran and Timmermann 1995

16. Literature Review: Stock Performance Prediction
Predominant approaches to stock prediction
Fundamentalists utilize fundamental and financial measures of economy, industry, and firm
Economy and sector indicators, financial ratios of the firm
Fama-French three factors model (Fama and French 1993)
Market return, market capitalization, book to market ratio
Currency exchange rates, interest rates, dividends
Technicians utilize historical time-series information of the stock and market behavior
Historical price, volatility, trading volume
Various machine learning models applied
Regression, ANN, ARIMA, support vector machines

17. Literature Review: Stock Performance Prediction
In addition to financial and stock variables, researchers have incorporated firm-related news article measures
Developed trend-based language models for news articles
Lavrenko et al. 2000
Categorized press releases (good, bad, neutral)
Mittermayer 2004
Examined various textual representations of news articles
Schumaker and Chen, 2009a; 2009b
But few have incorporated firm-related web forums
Thomas and Sycara (2000) utilize text classifications of discussions on Raging Bull to inform stock trading strategies

18. Literature Review: Firm-Related Web Forums and Stock
Studies relating web forums and stock behavior
Examined firm-related web forums on major web portals
Early studies focused on activity, without content analysis
Supported market efficiency; only concurrent relationships identified
Wysocki 1998; Tumarkin and Whitelaw 2001
Subsequently challenged; forum activity predicted stock behavior
Antweiler and Frank 2002; 2004; Das and Chen 2007
Analysis advanced to measure opinions in discussions
‘Bullishness’ classifiers to distinguish investment positions
Antweiler and Frank 2004; Das and Chen 2007
Classified buy, hold, or sell positions with 60 – 70% accuracy
Identified predictive relationships between forum discussion sentiment and subsequent stock returns, volatility, trading volume
Shortcomings
Retrospective analyses, shareholder perspective of major forums

19. AZ FinText: numbers + text
Techniques: bag of words, named entities, proper nouns, past stock prices + SVR
Testbed: S&P weeks, Oct-Nov 2005, 2,809 news, 10M stock quotes,
GICS industry classification
Evaluation: Return, vs. Quant funds; 20-minute prediction

20. AZ FinText in the news Thursday, June 10, 2010
AI That Picks Stocks Better Than the Pros
A computer science professor uses textual analysis of articles to beat the market.
WSJ Technology News and Insights
June 21, 2010, 1:45 PM ET
Using Artificial Intelligence to Digest News, Trade Stocks

21. AZ STOCK TRACKER I: mass, social media, topic, volume, sentiment
Data collection
Topic extraction
Conversation
analysis
Topic
Mutual information phrase extractor
Online
news
Web Forums
Traffic dynamics
Discussion
topics
Topic correlation and evolution
Spider/
Parser
Sentiment correlation and evolution
Sentiment aggregator
Author
Sentiment
Sentiment identification
Sentiment grader
Active topics and sentiments
Database
Market prediction
Message
sentiments
Message

22. User-Generated Contents (UGC): Conversations of 30,000 Wal-Mart Constituents and 500,000 Responses
Data sources
Duration
# of Threads
# of Messages
# of Users
Wall Street Journal
- WalMart-related News (WSJ)
Aug 1999
- Mar 2007
N/A
4,081
657
Yahoo! Finance
- WalMart Message Board (YAHOO)
Jan 1999
- Jun 2008
139,062
441,954
25,500
Walmart-blows Forum
- Employee Department Board (EMP)
Dec 2003
- Oct 2008
7,440
102,240
2,930
- WalMart Sucks Board (WSB)
Nov 2003
- Nov 2008
1,354
19,624
1,855
Wakeupwalmart Forum
- General WalMart Discussion Board (GDB)
Aug 2005
2,136
23,940
967

23. Post Dynamics

24. Sentiment Trend

25. Correlation coefficients with p<0.10 are shown (two-tailed test)
Market Modeling
Correlation
Return
Volatility
Trading Volume 1
0.0348
Sentiment
0.0338
Disagreement
Message Volume
0.3131
Message Length
0.0473
Subjectivity
Sentiment One Day Lag
Disagreement One Day Lag
Message Volume One Day Lag
0.3026
Message Length One Day Lag
0.0859
Subjectivity One Day Lag
Correlation coefficients with p<0.10 are shown (two-tailed test)
Correlation
Sentiment expressed in the forum contemporaneously correlates significantly with stock return
Disagreement, volume, and length expressed in the forum also hold significant correlations with volatility and trading volume

26. Market Predictive Results (cont’d)
Overall
Forum
Markett
Sentimentt-1
Disagreementt-1
Message Volumet-1
Message Lengtht-1
Subjectivityt-1
Returnt
0.8723***
(31.33)
0.0025
(0.31)
0.0000
(0.04) **
(-2.29)
0.0002
(1.42)
0.0015
(1.46)
Volatilityt
(-0.25)
0.0074
(0.47)
***
(-4.94)
***
(-19.09)
0.0030***
(7.82)
0.0149***
(7.27)
Trading
Volumet
0.7627***
(15.06) **
(-2.06)
0.0140**
(2.29)
0.1957***
(23.18)
***
(-13.24)
***
(-11.11)
Note: *p<0.10;**p<0.05;***p<0.01
Predictive regression (t-1)
The significant measures of forum discussions identified in contemporaneous regressions maintain their significance in the predictive regression models
Additionally, sentiment expressed in the web forum holds a significant relationship with the trading volume on the following day
Positive sentiment reduces trading volume; negative sentiment induces trading activity

27. AZ STOCK TRACKER II: stakeholder analysis

28. Experimental Design: Description of Prediction Models
Variables
Description
Dependent:
RETURN t
Stock return on day t (log difference of share price)
Fundamental:
FFSIZE
FFBTM
FFMARKET t-1
FFMARKET t-2
Fama-French firm size (prior year; market capitalization = share price * shares outstanding)
Fama-French book-to-market ratio (prior year; book value / market value of shares)
Fama-French market return on day t – 1 (log difference of S&P 500 index price)
Fama-French market return on day t – 2 (log difference of S&P 500 index price)
Technical:
RETURN t-1
RETURN t-2
VOLATILITY t-1
VOLATILITY t-2
VOLUME t-1
VOLUME t-2
DAY d t
Stock return on day t – 1 (log difference of share price)
Stock return on day t – 2 (log difference of share price)
Stock price volatility on day t – 1 (volatility modeled using a GARCH(1,1))
Stock price volatility on day t – 2 (volatility modeled using a GARCH(1,1))
Stock trading volume on day t – 1 (in log)
Stock trading volume on day t – 2 (in log)
Dummy variables for trading day of the week on day t
t = days (t = 1, 2, …, n); day of the week (d = 1, …, 4)

29. Experimental Design: Description of Prediction Models
Variables
Description
Forum:
MESSAGES t-1
LENGTH t-1
SENTI t-1
VARSENTI t-1
SUBJ t-1
VARSUBJ t-1
Number of messages posted in the forum on day t – 1 (in log (1 + messages))
Average length of messages posted in the forum on day t – 1 (in number of sentences)
Average sentiment of messages posted in the forum on day t – 1
Variance in sentiment of messages posted in the forum on day t – 1
Average subjectivity of messages posted in the forum on day t – 1
Variance in subjectivity of messages posted in the forum on day t – 1
Stakeholder:
MESSAGES s t-1
LENGTH s t-1
SENTI s t-1
VARSENTI s t-1
SUBJ s t-1
VARSUBJ s t-1
Number of messages posted by stakeholder cluster s on day t – 1 (in log (1 + messages))
Average length of messages posted by stakeholder cluster s on day t – 1 (in number of sentences)
Average sentiment of messages posted by stakeholder cluster s on day t – 1
Variance in sentiment of messages posted by stakeholder cluster s on day t – 1
Average subjectivity of messages posted by stakeholder cluster s on day t – 1
Variance in subjectivity of messages posted by stakeholder cluster s on day t – 1
t = days (t = 1, 2, …, n); stakeholder clusters (s = 1, 2, …, c)

30. Experimental Design: Description of Prediction Models
Baseline Model – Baseline-FF
Fundamental variables: Fama-French model
Baseline Model – Baseline-Tech
Technical variables: Lagged stock returns, volatility, trading volume, day-of-week dummies
Baseline Model – Baseline-Comp
Comprehensive: all fundamental and technical variables
Where t = days (t = 1, 2, …, n); day of the week (d = 1, …, 4)

31. Experimental Design: Description of Prediction Models
Forum models
Comprehensive baseline variables plus forum-level measures
Where t = days (t = 1, 2, …, n); day of the week (d = 1, …, 4); stakeholder clusters (s = 1, 2, …, c)

32. Experimental Design: Description of Prediction Models
Stakeholder models
Comprehensive baseline variables plus stakeholder group-level forum measures
Where t = days (t = 1, 2, …, n); day of the week (d = 1, …, 4); stakeholder clusters (s = 1, 2, …, c); index k = (((c - 1) * 6) + 15)

33. Experimental Design: Social Media Data
A 17 month period was utilized for analysis and experimentation
November 1, 2005 to March 31, 2007
First five months were utilized to calibrate the initial stock return prediction models
November1, 2005 – March 31, 2006
Calibrated models applied for prediction during each trading day in the next month
Each subsequent month, new models were calibrated using five previous months of time-series variables, for stock return prediction during the next month of trading
In total, stock return prediction was performed daily for one year (250 trading days)
April 1, 2006 – March 31, 2007
Forum
Messages
Discussion
Threads
Stakeholders
per Thread
Messages per
Stakeholder
Yahoo Finance – WMT
(finance.yahoo.com)
134,201
40,633
5,533
3.30
24.25
Wal-Mart Blows (
55,125
3,690
1,461
14.94
37.73
Wakeup Wal-Mart (
10,797
1,306
915
8.27
11.80

34. Results and Discussion
Hypothesis testing results
Hypothesis
Result
H1.1 Baseline-Comp model > Baseline-FF model
Partially supported
H1.2 Baseline-Comp model > Baseline-Tech model
Rejected
H2 Forum-level models > best baseline models
H3.1 Stakeholder-level models > best baseline models
Supported
H3.2 Stakeholder-level models > forum-level models
H4.1 Social network > discussion content representation
H4.2 Writing style > discussion content representation
H4.3 Social network > writing style representation
H5.1 ANN > OLS
H5.2 SVR > OLS
H5.3 SVR > ANN

35. Results and Discussion
Wal-Mart stock return prediction model results
Baseline models using fundamental and technical variables
Results across 250 trading days forecasted
Baselines for simulated trading (initial investment of $10,000):
Holding Wal-Mart stock for the year results in $10,096
Holding S&P 500 for the year results in $11,012
Model
OLS $
OLS Accuracy
ANN $
ANN Accuracy
SVR $
SVR Accuracy
Baseline-FF
$ 9,787
55.20%
$ 9,998
44.40%
$ 9,408
51.20%
Baseline-Tech
$ 8,799
57.20%
$ 9,702
57.60%
$ 9,503
56.40%
Baseline-Comp
$ 10,763
54.40%
$ 10,418
56.80%
$ 10,645

36. Results and Discussion
Wal-Mart stock return prediction model results
Incorporating the Wakeup Wal-Mart web forum
Results across 250 trading days forecasted
Model
OLS $
OLS Accuracy
ANN $
ANN Accuracy
SVR $
SVR Accuracy
Best Baseline
$ 10,763
57.20%
$ 10,418
57.60%
$ 10,645
56.80%
Forum
$ 10,367
$ 10,397
59.20%
$ 10,303
Stakeholder-SN
$ 9,873
55.20%
$ 10,930
$ 10,669
Stakeholder -Content
$ 10,689
60.40%
$ 11,595
$ 11,976
61.20% *
Stakeholder -Style
$ 10,271
56.00%
$ 9,653
$ 9,305
Stakeholder-SN+Content
$ 10,384
61.60%
$ 13,066
60.80%
$ 11,866
62.80% **
Stakeholder-SN+Style
$ 10,744
60.00%
$ 10,792
$ 11,249
Stakeholder-Content+Style
$ 10,696
$ 10,590
56.40%
$ 10,603
58.80%
Stakeholder-SN+Content+Style
$ 10,976
58.00%
$ 10,778
$ 10,881
59.60%
Pair-wise t-test; improvement over best baseline model at * p < 0.10 ** p < 0.05

37. AZ STOCK TRACKER III

38. Introduction Forward-looking statements (FLS) refer to
Projections, forecasts, or other predictive statements
Made by firm management
Section 21E of the Securities Exchange Act (1934)
Extended forward-looking statements (EFLS)
Statements that may have implications for a firms future development
Similar to FLS, but broader
Including information from information intermediaries (e.g., newspapers, newswires) and individuals (e.g., blogs)

39. Recognizing EFLS
EFLS: Extends FLS to include statements about firm’s future performance from other sources such as financial press, analysts’ reports, and individuals
Goal
Recognition Task
Definition
EFLS Recognition
Future Timing (FT)
Primary content is about future events or states
Explicit Uncertainty (EU)
Explicit accounts of doubt or unreliability
Overall Assessment (ALL)
Affect decision maker’s belief about a firm’s future cash flow
EFLS Sentiment
Positive (POS)
Positive impact on the belief
Negative (NEG)
Negative impact on the belief

40. AZ STOCK TRACKER III:
EFLS

41. Summary of Annotation Results
High kappa values (>0.7) on risks supports the coding scheme being empirically valid
Agreement upper bound
89% to 91% (for ALL, POS, and NEG)
Agreement
Cohen’s Kappa
ALL
0.91
(0.88, 0.93)
0.81
(0.76, 0.86)
POS
0.90
0.79
(0.73, 0.85)
NEG
0.89
(0.86, 0.91)
0.77
(0.71, 0.82)
Category
Count
Percent
ALL
1157
46%
POS
836
33%
NEG
904
36%
Reference Standard Dataset:
2539 sentences in total
kappa reference value 0.75
alpha reference value 0.7
DT=1  = 307
DT>1  184 rows
Note: (95% CI) from 1,000 Bootstrappings

42. Experiment 1: Sentence-Level Evaluation
Model
Accuracy†
F-Measure‡
Recall‡
Precision‡
LASSO
67.1%
66.5%
83.8%
55.1%
ENET75
69.3%
68.0%
87.7%
55.6%
ENET50
68.9%
68.7%
90.5%
55.4%
ENET25
69.4%
91.2%
SVM
69.5%
70.2%
83.9%
60.3%
SVM w/IG
69.1%
84.3%
58.3%
FKC
64.7%
50.9%
69.7%
40.1%
OF_PN
54.8%
27.9%
19.1%
51.4%

43. EFLS Impacts: Hypotheses Development
Theoretical framework (Easley and O’Hara, 2004)
There are 𝐼 𝑘 signals for stock k ( 𝑠 𝑘1 , 𝑠 𝑘2 , …, 𝑠 𝑘 𝐼 𝑘 )
𝑠 𝑘𝑖 ~𝑁 𝑣 𝑘 , 1 𝛾 𝑘
( 𝑠 𝑘1 , 𝑠 𝑘2 , 𝑠 𝑘3 , 𝑠 𝑘 (𝛼 𝑘 𝐼 𝑘 ) , 𝑠 𝑘 (𝛼 𝑘 𝐼 𝑘 +1) ,…, 𝑠 𝑘 (𝐼 𝑘 −1) , 𝑠 𝑘 𝐼 𝑘 )
𝛼 𝑘 : The relative amount of private-versus-public information
Private Signals
Public Signals

44. Hypotheses Development (Cont’d.)
Hypothesis 1: Firms with lower EFLS intensity are associated with higher expected return.
𝜕𝐸[ 𝑣 𝑘 − 𝑝 𝑘 ] 𝜕 𝛼 𝑘 = 𝛿 𝑥 𝑘 1− 𝜇 𝑘 𝐼 𝑘 𝛾 𝑘 𝐶 𝑘 𝛼 𝑘 𝐼 𝑘 𝜂 𝑘 𝜇 𝑘 2 𝛾 𝑘 𝜎 − >0

45. Hypotheses Development (Cont’d.)
Hypothesis 2: Firms with lower EFLS intensity are associated with the higher stock volatility.
If 𝐼 𝑘 𝛾 𝑘 > 𝜌 𝑘 and 𝜇 𝑘 > 2 −1 then 𝜕𝑉𝑎𝑟 𝑣 − 𝑝 𝑘 𝜕 𝛼 𝑘 >0
Intuition: if there are enough signals and the fraction of informed investors is larger than 41%, then firms with lower amounts of EFLS  Higher Volatility
𝜕𝑉𝑎𝑟( 𝑣 𝑘 − 𝑝 𝑘 ) 𝜕 𝛼 𝑘 = 𝛿 4 𝛾 𝑘 𝐼 𝑘 1− 𝜇 𝑘 2 𝛿 4 + 𝑉 1,𝑘 + 𝑉 2,𝑘 𝜂 𝑘 𝛿 2 𝜌 𝑘 + 𝛾 𝑘 𝐼 𝑘 (1+ 𝛼 𝑘 ( 𝜇 𝑘 −1)) + 𝛼 𝑘 𝜂 𝑘 𝛾 𝑘 𝐼 𝑘 𝜇 𝑘 2 ( 𝛾 𝑘 𝐼 𝑘 + 𝜌 𝑘 ) 3
𝑉 1,𝑘 = 𝛾 𝑘 𝐼 𝑘 − 𝜌 𝑘 + 𝜇 𝑘 𝛾 𝑘 𝐼 𝑘 + 𝜌 𝑘 𝛼 𝑘 𝜂 𝑘 2 𝐼 𝑘 𝛾 𝑘 𝜇 𝑘 2 + 𝛿 2 𝜂 𝑘
𝑉 2,𝑘 = −1+2 𝜇 𝑘 + 𝜇 𝑘 2 𝛿 2 𝜂 𝑘 𝛾 𝑘 𝐼 𝑘 𝛼 𝑘

46. Control Variables Variable Definition
Number of news articles mentioning firm i in month t.
Logarithm of market value, computed using the closing market price of month t-1.
Logarithm of book-to-market ratio, computed following Fama and French (1993).
Log(Dollar trading volume of firm i in month t)
Log(variance); variance of firm i in month t is computed using daily stock returns.
Proportion of individual ownership of stock i, using the latest available data, computed by aggregating 13f filings (Fang and Peress 2009).
Log(1+number of analysts covering firm i in month t).
Log(1+standard deviation of analyst’s earnings predictions).

47. Firm-Level Performance Evaluation (Cont’d.)
Empirical Model 1:
Empirical Model 2:
Hypothesis 1 Predicts Negative b1
𝑟 𝑖,𝑡+1 = 𝑎 0 + b 1 𝐴𝐿𝐿_𝐼𝑁 𝑖,𝑡 + 𝑐 1 𝑁𝑒𝑤𝑠𝐹𝑟𝑒 𝑞 𝑖,𝑡 + 𝑐 2 𝑁𝑒𝑤𝑠𝑆𝑒𝑛𝑡 𝑖 𝑖,𝑡 +
𝑑 1 𝐿𝑜𝑔𝑆𝑖𝑧 𝑒 𝑖,𝑡 + 𝑑 2 𝐿𝑜𝑔𝐵 𝑀 𝑖,𝑡 + 𝑑 3 𝑟 𝑖,𝑡 + 𝑑 4 𝐿𝑜𝑔 𝑉 𝑖,𝑡 + 𝑒 𝑖𝑡
Hypothesis 2 Predicts b1 ≠ 0
𝐿𝑜𝑔𝑉 𝑖,𝑡+1 = 𝑎 0 + b 1 ALL_IN i,t + 𝑐 1 𝑁𝑒𝑤𝑠𝐹𝑟𝑒 𝑞 𝑖,𝑡 + 𝑐 2 𝑁𝑒𝑤𝑠𝑆𝑒𝑛𝑡 𝑖 𝑖,𝑡 +
𝑑 1 𝐿𝑜𝑔𝑉𝑜𝑙𝑢𝑚 𝑒 𝑖,𝑡 + 𝑑 2 𝐿𝑜𝑔 𝑉 𝑖,𝑡 + 𝑑 3 𝐿𝑜𝑔𝑆𝑖𝑧 𝑒 𝑖,𝑡 +
𝑑 4 𝐿𝑜𝑔𝐵 𝑀 𝑖,𝑡 + 𝑑 5 𝑟 i,t + 𝑑 6 𝐼𝑛𝑑𝑣𝑂𝑤 𝑛 𝑖,𝑡 +
𝑑 7 𝐿𝑜𝑔𝐴𝑛𝑎𝑙𝑦𝐶𝑜𝑣𝑒 𝑟 𝑖,𝑡 + 𝑑 8 𝐿𝑜𝑔𝐴𝑛𝑎𝑙𝑦𝑆 𝐷 𝑖,𝑡 + 𝑒 𝑖,𝑡

48. Experiment Two: Firm-Level Evaluation
Research Testbed: January 1986 to May 2008, 1,134,321 Wall Street Journal news articles
Merged with CRSP, Compustat, and IBES
Stock prices lower than $5 at the end of a month were removed (Cohen and Frazzini 2008; Fang and Peress 2009)
1,274,711 firm-months, spanning 269 months

49. Expected Return and EFLS Intensity
Variable
Value * **
Control Variables
***
***
*** **
***
0.0025***
-0.046***
Intercept
0.039***
0.0031
***, **, * indicate statistical significance at the 0.01, 0.05, and 0.1 levels, respectively.

50. Volatility and EFLS Intensity
Model 2A (𝐴𝐿𝐿_𝐼 𝑁 𝑖,𝑡 )
Model 2B (𝐹𝑇_𝐼 𝑁 𝑖,𝑡 )
Model 2C (EU_𝐼 𝑁 𝑖,𝑡 )
Variable
Value
𝐴𝐿𝐿_𝐼 𝑁 𝑖,𝑡
-0.074***
𝐹𝑇_𝐼 𝑁 𝑖,𝑡
-0.196***
𝐸𝑈_𝐼 𝑁 𝑖,𝑡
-0.254***
Control Variables
𝑁𝑒𝑤𝑠𝐹𝑟𝑒 𝑞 𝑖,𝑡
0.012***
𝑁𝑒𝑤𝑠𝑆𝑒𝑛𝑡 𝑖 𝑖,𝑡
-0.105***
-0.103***
-0.110***
𝐿𝑜𝑔𝑉𝑜𝑙𝑢𝑚 𝑒 𝑖,𝑡
0.108***
𝐿𝑜𝑔 𝑉 𝑖,𝑡
0.565***
𝐿𝑜𝑔𝑆𝑖𝑧 𝑒 𝑖,𝑡
-0.222***
𝐿𝑜𝑔𝐵 𝑀 𝑖,𝑡
-0.066***
𝑟 𝑖,𝑡
-0.615***
-0.616***
𝐼𝑛𝑑𝑣𝑂𝑤 𝑛 𝑖,𝑡
0.071***
𝐿𝑜𝑔𝐴𝑛𝑎𝑙𝑦𝐶𝑜𝑣𝑒 𝑟 𝑖,𝑡
0.016***
0.017***
𝐿𝑜𝑔𝐴𝑛𝑎𝑙𝑦𝑆 𝐷 𝑖,𝑡
0.095***
Intercept
-1.568***
-1.566***
𝑅 2
0.57
***, **, * indicate statistical significance at the 0.01, 0.05, and 0.1 levels, respectively.

51. Take-Away and WIP (20%)
Mass and social media texts provide additional signals for market prediction (in addition to numbers)
Message volume important; aggregate sentiment may not (EMH)
Business sentiment processing difficult; may require additional content pre-processing (stakeholder; EFLS)
Predicting return hard; predicting volatility easier (VIX Chicago Board)
Large-scale stock news tracking and text analytics can be automated
Trading windows; decay function; targeted sentiment; extensive trading periods (up/down); industry and news category (oil/banking); firm & index size (Russell/NYSE); emerging markets (China)
 All the firms (10K), all the news (1M each), all the time ???
 Trading strategy ???

52. AZ BIZ INTEL System Design
Predefined Data Sources
Data Sources for US Public Companies
SEC/Edgar
NYSE.com
NASDAQ.com
Finance.Yahoo.com
Company Information Database
Ticker
CUSIP
CIK
PERMNO
Company Keywords
Company Name
Dynamic Data Sources
Blogs
News
Search Engines
WSJ
Twitter
Basic Information
Yahoo Finance Forums
Company Websites
Stock Exchange
10K Report
Data Collection
Data Processing
Transformation/Integration
Topics & Sentiments
Time Series / Burst
Risk Model
SNA
Data
Analysis
Analytic Approaches
Performance Indicators
Cross Media Analysis
Single Media Analysis
Predictive
AZ BIZ INTEL System Design
Static Figures/Dashboards
Interactive Applications
Visualization
Simulated Trading

53. Hsinchun Chen, Ph.D.
Artificial Intelligence Lab, University of Arizona