Blog #4: The Nitty Gritty

Sai G -

Understanding the Effects of Media Sentiment on Stocks and Businesses

Welcome back, readers! If you don’t know me, my name is Sai, and I’m here to give you a few updates since last week’s work. 

Firstly, I have definitely finished collecting all my data to establish the media sentiment this time. As I was reviewing my work, I realized I had made a mistake whilst coding, so I had to regather the data for my data sets. I’ve also made some steady progress toward my data synthesis. So, since I’ve collected all my data, I now have to make it suitable for synthesis. I’ve spent this past week debugging the code and its errors in scraping for article information. So, I had originally planned for my code to be able to scrape all the relevant article information such as title, text, and publishing dates; however, the code wasn’t able to do this for all the data because of paywalls and other annoying security measures, so I’ve had to manually gather some of this information for many of my articles, so it’s been both tedious and time-consuming. 

Since I’ve now finished preparing all the article information, the next step is to gather the polarity and subjectivity scores for each article using Textblob, a Python module. Now, for this, I had also originally planned it to be automated, but unfortunately, that didn’t pan out because of the ads and other extraneous text being lumped in. So, to resolve this, I’ve been manually copying the article into the code to analyze. So, this has added to this week’s tedious labor, but nonetheless, I’ll prevail. 

Those have been the main things I’ve been working on this week, and hopefully, by next week, I can start putting the data together to finally synthesize some results. 

On another note, this week has been very busy, and I’ll be flying out to Boston as well later this week, so I’ll be putting my research on hold for a little while, and get back into it soon after. I’m very excited about Boston and my research’s progress, but that’s all I have for you guys this week. See you next week. 

More Posts

Comments:

All viewpoints are welcome but profane, threatening, disrespectful, or harassing comments will not be tolerated and are subject to moderation up to, and including, full deletion.

    avni_c
    This all sounds really interesting Sai! Just for clarification, however, what is your definition of “media sentiment” in your project's context? Is it toward a specific topic, or just a general tone?
    sai_g
    Good question! See, for this project, I'll be defining “media sentiment” as the overall tone (positive, negative, or neutral) of online articles specifically discussing the chosen influencer products. I'll analyze the sentiment, which is measured through the gathered polarity and subjectivity scores, and see how it correlates with fluctuations in stock prices. By looking at the combined 300 articles on Yeezy’s, Prime Hydration, and Kylie Cosmetics, I hope to see the effects of media perception on consumer trust and business performance.

Leave a Reply

Your email address will not be published. Required fields are marked *