Computer Science. Data Mining from Twitter Using P

Computer Science. Data Mining from Twitter Using Python

The primary theme of the paper is Computer Science. Data Mining from Twitter Using Python in which you are required to emphasize its aspects in detail. The cost of the paper starts from $159 and it has been purchased and rated 4.9 points on the scale of 5 points by the students. To gain deeper insights into the paper and achieve fresh information, kindly contact our support.

The Project Involves Mining data from twitter about apple’s new mobile device the Iphone x. I want to get information on how people feel about the latest apple device flagship and determine whether more people feel good about the device or more people feel bad about the device.

• In THIS REGARD, I am to develop a system(program) that would perform sentiment analysis on data(tweets) received from twitter using the Twitter Streaming API. I have already built code for collecting the tweets as I used keywords : ‘iphone x’, ‘iphone 10’, #iphonex, “iphone 10’, ‘iphone ten’ to filter the tweets about the iphonex device. I have also saved the received tweets in a text file called phonecorpus.txt
• From my understanding so far, the data received from twitter should be stored in a text file for further pre-processing. In order to do sentiment analysis, I would need to pre-process the received tweets. Pre-processing operations include Removal of URLS, Spelling corrections, stopword removal, removal of non-english tweets, removal of punctuations and numbers etc.
• The data obtained from the streaming API contains many attributes eg( created_at: , location: , favourite_count etc. for the sentiment analysis, I feel only the “text:” field will be needed.
• The sentiment analysis code should be able to analyze the text file containing the tweets and categorize the tweets into negative and positive tweets. Afterwards, a pie chart should be generated showing the percentage of negative tweets to positive tweets (all by using relevant python libraries). On the pie chart, the positive tweets should be denoted in blue colour and the negative tweets should be denoted in red colour. Also, code should be provided that will count the total number of positive and negative tweets.
• Lastly, There should be code that would extract URL links for reviews about the iphonex (Please note that the links should be extracted from the text-file containing the twitter data that has been streamed).

NB: Please code should be well commented so I can understand what each block is doing. Also maybe a report saying the steps/techniques carried out would be helpful. For this project I suppose you would use functions to build code. You can explain what each function does. s