Large-scale Comparative Sentiment analysis of News Articles

Summary:

Although a large volume of new items are available to the public due to online media, there is a lack of efficient ways analyze them.  This article presents sentiment analysis as a visual tool for analyzing news items.  This tool in combination with text analysis is designed to analyze news feeds from Europe Media Monitor (EMM) to determine if they have positive or negative connotations.  Since this technique is semi-automatic, it costs less and is capable of monitoring a specific topic real-time.  The news articles gathered focused on two categories; terrorist attacks and natural disasters.  A sentiment score was given to each of the 6000 news articles related to terrorist attacks, and 1000 new articles related to natural disasters. 

Sentimental analysis not only provides effective visual representation of the data but also highlights trends and patterns. For example, figure one displays new articles of one week. The vertical axis shows the week divided in to days and the horizontal axis shows the time the article was published. Each triangle represents a news feed which is color coded as red (negative news item), blue (positive news item), or white (neutral news item). While the upper line contains news associated with terrorist attacks and the lower line contains news associated with natural disasters. News articles associated with both categories are placed in between both lines.  News articles with more saturated colors have higher sentiment scores.  Utilizing the zoom function, one may look at each triangle without data overlap.      

From this experiment, the authors were able to retrieve and asses a large volume of news articles from EMM. The data was organized utilizing the time and date they were published. A sentiment score was given to each article based on the tone associated with each article.

Critique:

This article explains a scenario that uses sentiment analysis to evaluate news articles.  However, it does not provide a good introduction to the experiment.  For example, the authors do not explain why the study was conducted or how a sentiment score was assigned to each news article. The authors mostly emphasized sentiment analysis as a visual tool, but did not explain the software used to analyze the articles. In addition, it does not assess advantages and disadvantage of this type of study. Sentimental analysis can analyze current activities on social networking sites. However, it can be subjective in interpretation because information found on articles is prone to biases.              

Utilizing sentiment analysis for assessing media is fairly new concept that has gone viral in the past few years.  It has similarities to social media analysis.  Sentiment analysis is a great technique for businesses attempting to improve quality of customer care.  They may utilize sentiment analysis to evaluate what is being discussed on media sites. If the feedback is negative, then the company can take proper action to improve the quality of customer service.  Also, based on positive and negative reviews, decision makers can formulate strategies to improve sales and marketing efforts.   

 
Source:
Rohrdantz, F., Mansmann, F., Stoffel, A., Kristajic, M., & Keim, D. (n.d.). Large-scale comparative   sentiment analysis of news articles. Retrieved from http://www.inf.uni-konstanz.de/gk/pubsys/publishedFiles/WaRoMa09b.pdf http://www.inf.uni-konstanz.de/gk/pubsys/publishedFiles/WaRoMa09b.pdf