fix a bug

proposal.tex

@@ -54,7 +54,7 @@ \subsection*{Evaluation}
 even though such accuracy may not sound impressive. If a program were "right" 100\% of the time, humans would still disagree with it about 20\%
 of the time. Therefore, I planned to compare the performance with a popular sentiment analysis Web service: Google Prediction.
 \section*{Expected Outcomes}
-Because of the methods that I used might not be the state of the art techniques, I expect the performance might not be as good as Google prediction.
+Because of the methods that I used might not be the state of the art techniques, I expect the performance might not be as good as Google Prediction.
 However, the performance should be higher than random selection, that is, higher than 50\% accuracy.