Sentiments Analysis on #Jiocinema
Used snscrape for tweets scraping and python’s data visualisation libraries for getting insights.
As a data scientist, I often find myself analyzing large amounts of data, looking for patterns and insights that can help me understand the world around me. Recently, I decided to put my skills to the test by conducting a sentiment analysis of tweets related to #jiocinema during IPL 2023.
Now, for those of you who don’t know, IPL is a cricket tournament that takes place in India every year, and it’s kind of a big deal. This year, for the first time ever, the tournament was being streamed on the Jio Cinema app. Naturally, cricket fans were excited to watch their favorite teams battle it out on their screens.
As a cricket fan myself, I was curious to see what people were saying about the Jio Cinema app and the streaming experience. So, armed with my trusty tools (Python, TextBlob, WordCloud, and Matplotlib), I dove into the world of #jiocinema tweets.
Analysis:
And let me tell you, there were a lot of tweets. Some were positive, some were negative, and some were just plain hilarious. Here are some of my favorite tweets from the analysis:
- “Trying to watch #IPL2023 on the Jio Cinema app is like trying to watch a cricket match in the middle of a storm. Just when you think things are looking up, everything goes haywire.”
- “I never thought I’d say this, but thank god for the commentary in Bhojpuri. It’s the only thing keeping me sane while this app keeps buffering.”
- “Watching IPL on Jio Cinema app is like watching a thriller movie with the worst buffering speed. It’s ruining the climax every time.”
As you can see, people had some strong feelings about the app’s performance. But despite the technical issues, the sentiment analysis revealed that the majority of tweets were actually neutral. It seems that cricket fans were able to put up with the buffering and crashing for the sake of watching their favorite teams in action.
As you can see from the pie chart above, 52.1% of the tweets were neutral, 30.7% were positive, and 17.2% were negative. The positive sentiment was likely driven by the return of MS Dhoni, one of India’s most beloved cricketers, who was playing in the tournament after a long hiatus. The availability of commentary in multiple languages also seemed to be a hit with viewers.
To get a better sense of the most common words used in the tweets, I used the WordCloud library to create a word cloud. Here’s what it looks like:
As you can see, words like “free”, “ipl” and “msdhoni” were used frequently in the positive tweets. It’s clear that even with the technical issues, people were still enjoying the cricket and the overall experience.
Of course, there were also plenty of negative tweets, as the analysis revealed. The buffering and crashing issues were the most common complaint, as we can see from the negative word cloud below:
Words like “buffering,” “worst,” and “jiocrash” were used frequently in the negative tweets. It’s understandable that people would be frustrated by these issues, especially when trying to watch a live sporting event.
The world of social media has opened up new avenues for businesses to engage with their customers and receive feedback. Despite some technical issues, the sentiment was mostly neutral, with a significant number of positive tweets. This can be attributed to factors such as the return of MS Dhoni and the availability of commentary in multiple languages, including Bhojpuri, which generated some hilarious tweets.
The availability of commentary in regional languages highlights the importance of catering to the diverse Indian audience. The positive response to Bhojpuri commentary on the Jio Cinema app suggests that providing content in regional languages can be a significant factor in engaging viewers. This finding can be useful for streaming platforms to improve their viewership experience and retain their customers.
In conclusion, the sentiment analysis and topic modeling provided some valuable insights into the IPL viewership experience on Jio Cinema. The analysis showed that despite technical issues, the overall sentiment was mostly neutral, with a significant positive sentiment. The availability of commentary in multiple languages, including regional languages, is a significant factor in engaging viewers. These insights can be useful for streaming platforms to improve their viewership experience and cater to the diverse Indian audience. As an emerging data scientist, this was an enriching experience that provided a glimpse into the world of social media analytics and the potential it holds for businesses.
Pie Chart: After discussing the sentiment analysis results, a pie chart showing the percentage breakdown of neutral, positive and negative tweets can be included.
Bar Chart: A bar chart showing the distribution of tweets over time can be included to depict the tweet volume trend.
Positive Word Cloud: A word cloud showing the frequently used positive words in IPL tweets related to Jio Cinema can be included.
Negative Word Cloud: A word cloud showing the frequently used negative words in IPL tweets related to Jio Cinema can be included.
Technical Aspects:
Now that we have analyzed the sentiments and topics being discussed in IPL tweets related to Jio Cinema, let’s delve deeper into the techniques used to perform the analysis.
For scraping data from Twitter, I used the snscrape library, which provides an easy-to-use interface to fetch tweets using various search parameters. One of the advantages of using snscrape is that it does not require any authentication or API keys, making it more accessible for beginners.
Once I had scraped the tweets, I used Natural Language Toolkit (nltk) and TextBlob libraries to preprocess the text data. These libraries offer a variety of functions to tokenize, lemmatize, remove stopwords and perform sentiment analysis.
For visualizations, I used the Matplotlib library to create bar charts and pie charts to depict the tweet volume trend and the distribution of sentiments respectively. I also used the WordCloud library to create word clouds showing the frequently used positive and negative words in IPL tweets related to Jio Cinema.
Another challenge was dealing with the noise in the data. Twitter is notorious for being a platform where people express their opinions, sometimes in a not-so-polite manner. This meant that the data contained a lot of irrelevant and sometimes offensive content that had to be removed to perform a meaningful analysis.
Despite these challenges, the sentiment analysis provided valuable insights into the IPL viewership experience on Jio Cinema. As a data scientist, it was exciting to apply these techniques to a real-world problem and see the insights that can be gained from analyzing social media data.
To access the code, please visit my Github page: https://github.com/BhupeshRathore07/Data-Analysis-Project-Tweets-Sentiments-Analysis-Jio-Cinema-App.
🤝 And if you have any questions, comments, or suggestions, please don’t hesitate to reach out to me. You can find me on LinkedIn or drop me an email at bhupeshrathore932@gmail.com . I’m always happy to connect and discuss all things data science! 💬
🎉 And with that, we’ve come to the end of this blog! Thank you so much for taking the time to read it and explore the fascinating world of data science with me. But don’t worry, this is just the beginning of our journey! 🚀 Stay tuned for more intriguing insights and exciting projects as we continue to delve deeper into the realm of data science.
