Twitter_Sentiment_Analysis is a program which performs sentiment analysis of Twitter data---that is, determining the "attitude" of tweets (how "positive" or "negative") about a particular topic. We will apply this program to real data taken directly from Twitter, and use our analysis to consider basic questions about people's attitudes on social media.
Submitted by: Zhengrui Lu, Xinyi Wu
Time spent: 30 hours spent in total
The following functionality is completed:
- Sort data from Twitter API
- Efficient Textual Data Cleaning using Python
- Scalable Statistics using SciPy & Pandas & Bokeh & Numpy
- Pair programming: provide 2 versions code solutions to achieve objects
- 600+ Lines of Code in Total
- Support for mental health and well-being
Here's a sample of implemented project stories:
This project involves working with real, unfiltered, unsanitized data taken directly from the Twitter "firehose"--all public tweets made. Tweets may include offensive, inappropriate, or triggering language or content. As with the rest of the Internet, any given moment on Twitter can reveal both the peaks and valleys of human behavior. If you are concerned about this data in any way, please let us know.
AFINN is a list of English words rated for valence with an integer
between minus five (negative) and plus five (positive). The words have
been manually labeled by Finn Årup Nielsen in 2009-2011. The file
is tab-separated. There are two versions:
AFINN-111: Newest version with 2477 words and phrases.
AFINN-96: 1468 unique words and phrases on 1480 lines. Note that there
are 1480 lines, as some words are listed twice. The word list in not
entirely in alphabetic ordering.
An evaluation of the word list is available in:
The list was used in:
Lars Kai Hansen, Adam Arvidsson, Finn Årup Nielsen, Elanor Colleoni,
Michael Etter, "Good Friends, Bad News - Affect and Virality in
Twitter", The 2011 International Workshop on Social Computing,
Network, and Services (SocialComNet 2011).
This database of words is copyright protected and distributed under
"Open Database License (ODbL) v1.0"
http://www.opendatacommons.org/licenses/odbl/1.0/ or a similar
copyleft license.
Based on assignments by John DeNero, Aditi Muralidharan, et al., and Bill Howe.