The goal of portfolio management is to maximize investment returns while reducing investment risk. Reinforcement learning-based portfolio management continuously seeks characteristics in past data to maximize returns. Existing financial text information processing methods are not optimized for investment decision events, making it difficult to accurately reflect the actual impact of financial text information on investment. Additionally, differences in the quality of financial text information result in noisy data. In view of these limitations, this research proposal has two main goals. The first goal is to find effective ways to extract signals present in the financial news and the second goal is to eventually use the signals from the news articles to improve portfolio management. More specifically, in our proposal we focus on analysing sentiment signals from the financial news articles and we observe the effect of the sentiment scores on reinforcement learning based portfolio management approaches. We did an initial investigation to observe the effect of sentiment scores in portfolio management. In our experiments, we randomly selected eight stocks from Dow Jones Industrial Average index for experiments and verified that our model can significantly improve cumulative returns 117.3% while reduce max drawdown 15.2%. It greatly improves the performance of reinforcement learning-based investment management methods.