The Wiley Finance Series : Handbook of News Analytics in Finance

6.3 News data structure and statistics We are using data from the Thomson Reuters NewsScope Sentiment Engine (RNSE), developed w ...

154 News and abnormal returns Figure 6.2. Sample RNSE data. Quantitative scores on qualitative information. Relevance measures h ...

takes for people to accumulate information. This type of signal is amenable to large- position building and higher capacity fund ...

.Intensity One or two unique news items per day minimum. .Relevance How much the article is about a particular firm (60%). .Sen ...

The first event study was very simple and broad, designed to compare with Tetlock, Saar-Tsechansky, and Macskassy’s earlier resu ...

6.5 REFINING FILTERS USING INTERACTIVE EXPLORATORY DATA ANALYSIS AND VISUALIZATION There are many ways to slice and dice event s ...

identifier) and can be subset by time period, sector, market capitalization, or attributes of the RNSE news that occurred on tha ...

160 News and abnormal returns (a) Figure 6.10.Turning the knob up from the 90th percentile (a) to the 95th percentile (b) on the ...

Relating news analytics to stock returns 161 (a) Figure 6.11.The same effects described for financials, but in the non-cyclical ...

6.6 Information efficiency and market capitalization An interesting question to investigate using the Event Study Explorer is th ...

6.7 US portfolio simulation using news analytic signals Event studies are screening methods that show potential value, but they ...

good reasons to hypothesize that investors can take a longer time to process new information that has extreme sentiment. Behavio ...

Transaction costs were simulated at 25 basis points of slippage and commission for the combined entry and exit of each position. ...

6.7.5 Portfolio characteristics Few firms have large amounts of novel, extremely polarized news. This strategy made active bets ...

Relating news analytics to stock returns 167 Figure 6.18.P/L of positions taken by the RNSE Extreme Sentiment Day strategy. The ...

6.8 Discussion of RNSE and portfolio construction We have shown that it is possible to capitalize on news by looking at days on ...

which the human is processing the information, often called ‘‘market color’’. Incor- porating this information from ‘‘traditiona ...

show positive results similar to ours, reflecting improvements in news processing in recent years. 6.9 Summary and areas for add ...

bullish or bearish sentiment about a given stock, vs. news that induces confusion in its readers as it unfolds. .Intraday analys ...

Tetlock P.; Saar-Tsechansky M.; Macskassy S. (2008) ‘‘More than words: Quantifying language (in news) to measure firms’ fundamen ...