Tweets are frequently used to express opinions, specifically when the topic of choice is polarizing, as it is in politics. With many variables effecting the choice of vote, the most effective method of determining election outcome is through public opinion polling. We seek to determine whether Twitter can be an effective polling method for the 2016 United States general election. To this aim, we create a dataset consisting of approximately 3 million tweets ranging from September 22nd to November 8th related to either Donald Trump or Hillary Clinton. We incorporate two approaches in polling voter opinion for election outcomes: tweet volume and sentiment. Our data is labeled via a convolutional neural network trained on the sentiment140 dataset. To determine whether Twitter is an indicator of election outcome, we compare our results to three polls conducted by various reputable sources during the 13 days before the election. Our results show that when using tweet sentiment, we obtain similar margins to polls conducted during the election period and come close to the actual popular vote outcome.