[PDF] [PDF] Campus sentiment analysis using Twitter data - Cal State Fullerton

[PDF] A focus on students use of Twitter – their interactions with - CORE

Sarah Prestridge, Griffith University, Mt Gravatt Campus, Brisbane, QLD 4111, Australia students' use of Twitter when it was implemented as a learning device

[PDF] Canyon ISD Communication through Twitter

There are three ways to receive CISD and campus Twitter communication 1 Receive Cell PhoneTexts of CISD Tweets: Anyone in the U S can receive texts of  

[PDF] 2021 University Program Opportunities - Twitter Careers

The mission of Twitter's Rotational Associate Product Manager (APM) program is to develop the next generation of product managers Through training, 

[PDF] Twitter to SMS Text Help - University of Guelph

Emergency Notification Twitter account directly to your phone as an SMS text message This is especially useful for non-registered users who are on campus

[PDF] Using Twitter in university research, teaching and - LSE Blogs

how Twitter can be used as a resource for research, teaching and impact Postgraduate and Master students are only based on campus for a short time (at  

[PDF] Campus sentiment analysis using Twitter data - Cal State Fullerton

Campus Sentiment Analysis Using Twitter Data Afshin Karimi Sunny Moon Rohit Murarka Office of Assessment and Institutional Effectiveness CSU Fullerton

[PDF] Examining Twitter Influence of Campus Executives - HubSpot

Campus Sonar and Dr Ahlquist identified six steps to starting an intentional executive presence on Twitter, or to assist an executive with strategy development 1

[PDF] twitter careers benefits

[PDF] twitter careers detroit

[PDF] twitter careers entry level

[PDF] twitter careers finance

[PDF] twitter careers legal

[PDF] twitter careers new grad

[PDF] twitter careers.m

[PDF] twitter database

[PDF] twitter design pattern

[PDF] twitter feed widget for website

[PDF] twitter for pc free download windows 10

[PDF] twitter for pc free download windows 7

[PDF] twitter for windows 8 pc download

[PDF] twitter hashtag widget for website

[PDF] twitter idubbbztv

PRESENTATION TITLE

Campus Sentiment Analysis Using Twitter Data

Afshin Karimi

Sunny Moon

Rohit Murarka

Office of Assessment and Institutional Effectiveness CSU Fullerton

2017 CAIR Conference - Concord, CA

Sentiment Analysis

Sentiment analysis (or opinion mining) : uses natural language processing and tedžt analysis to determine author's attitude towards a particular topic in a piece of text

Basic tasks:

Determine polarity (positive/negative/neutral)

Determine subjectivity/objectivity

More advanced tasks include examining emotional states such as anger, sadness, happiness

Opinion Mining in Different Industries

American Red Cross uses the SaaS tools of Radian6 to monitor social media comments made by its volunteers and donors (in addition to survey and in- person focus groups) The Wall Street Journal's Sentiment Tracker tracks Facebook Θ Twitter users. They share their findings not as scientific public opinion polls, however. Dell's Z^}]oMedia Listening Command Center' responds to serǀice related questions and complaints and monitors for consumer trends Proctor & Gamble, American Express, DirecTV other corporations with

Approach

Tweet Downloader (through Twitter API)

Feature (sentiment) Extraction

Classical machine learning methods to do polarity classification heavily dependent on training data Other methods use external lexical resources like WordNet, or SentiWordNet that identify polarity of words along with intensity Building a Twitter classifier model not the goal in this presentation (we use an existing RapidMiner operator for this)

Challenges of Sentiment Extraction

What a pronoun, or a noun phrase refers to. "We watched the movie and went to dinner; it was awful." What does "It" refer to? Parsing - What is the subject and object of the sentence, which one does the verb and/or adjective actually refer to? Sarcasm - If you don't know the author you have no idea whether 'bad' means bad or good. Twitter - acronyms, lack of capitals, poor spelling, poor punctuation, poor grammar Detecting more in depth sentiment/emotion (beyond positive/negative):

Tokenization/Text Processing

sentences, etc.) Choose a schema for processing Tweets (TF/IDF, Term Frequency, Term

Occurrence)

Use the created vectors (list of words) along with Tweet sentiments in

Tableau

RapidMiner Demo.

Final Word list (no filtering)

Visualization

Format the data

Build Tableau dashboards at both Tweet and word levels

Cluster Analysis

Use the vector of words (or select subset of them) to form clusters of tweets such that tweets in cluster are similar to each other and are dissimilar to tweets in other clusters # of Tweets per Day

Polarity & Subjectivity

Subjectivity of Tweets

Final thoughts

Enormous amount of unstructured data available

Automatic Sentiment Analysis challenging by nature; no perfect tool (yet!) No expertise required for basic Sentiment Analysisquotesdbs_dbs21.pdfusesText_27