Pre-symposium tutorial, November 8

Practical Sentiment Analysis

The Sentiment Analysis Symposium will be preceded Tuesday afternoon, November 8 by a three-hour tutorial, Practical Sentiment Analysis, 2:00 pm to 5:30 pm, designed for and taught by Christopher Potts of Stanford University that will include a 20-minute session covering the solution-provider marketplace and tool selection taught by symposium chair Seth Grimes. There will be a 30-minute break.

The tutorial will take place in the Bar Association of San Francisco facility, in the Bently Reserve building at 301 Battery Street, San Francisco.

You may register for the tutorial or the symposium or both.


To be presented by Christopher Potts (sessions of 90 and 70 minutes)

The amount of user-generated content on the Internet has risen exponentially over the last decade, and such content is now always at our fingertips. As a result, nearly all our decision-making is social; before buying products (attending events, trying services, voting for candidates, visiting specialists), we see what our peers are saying about them. The fate of a new offering is often sealed by those evaluations.

Sentiment analysis, the computational study of how opinions, attitudes, emotions, and perspectives are expressed in language, provides a rich set of tools and techniques for extracting this evaluative, subjective information from large datasets and summarizing it. It can thus be vital to service providers, allowing them to quickly assess how new products and features are being received. Recent breakthroughs mean that this analysis can go beyond a general measure of positive vs. negative, isolating a fuller spectrum of emotions and evaluations and controlling for different topics and community norms.

The tutorial will cover all aspects of building effective sentiment analysis systems for textual data, with and without sentiment-relevant meta-data like star ratings, helpfulness assessments, and demographic information. We will go from pre-processing techniques to advanced uses cases, assessing common approaches and identifying best practices at each stage. Attendees are encouraged to bring laptops; all the major components of the tutorial will include hands-on demos of the associated technology, enabling practitioners to gain first-hand experience with the strengths and limitations of a variety of approaches.

  1. Sentiment in language and cognition: brief overview of results from linguistics and cognitive psychology concerning the dimensions of affectivity and the ways in which attitudinal and emotional information is expressed. Special focus on going beyond positive/negative sentiment to capture more nuanced dimensions and perspectives.
  2. Text preparation: efficient, practical pre-processing steps for sentiment analysis, focussing on (i) sentiment-aware tokenization, (ii) approximating the semantic effects of negation, hedging, and prosody, (iii) identifying multi-word sentiment expressions, and (iv) pooling data from heterogenous sources.
  3. Sentiment lexicons: current approaches, publicly available resources, techniques for developing sentiment lexicons that adapt to specific data sets and tasks, and common pitfalls.
  4. Models for sentiment extraction and analysis: the pros and cons of sentiment classification, alternatives to classification, and an assessment of common supervised and unsupervised machine learning algorithms in the context of sentiment-related tasks.
  5. Context sensitivity: sentiment is highly variable and context-dependent; we will focus on methods for bringing information about topics/attributes, demographics, and community norms into sentiment analyses, for use-cases in which such information is available as textual meta-data and for use-cases in which it is not.
  6. Sentiment summarization: visualization techniques that summarize the way sentiment varies over time and among different groups, informed by results from cognitive psychology and human--computer interaction.
  7. Sentiment and social networks: a brief overview of the ways in which sentiment analysis can inform social network analysis, and the ways in which social relationships can guide sentiment analysis.
To be presented by Seth Grimes (20 minutes)
  1. A survey of the solutions marketplace.
  2. How to evaluate vendor claims and find the right provider.


You may register for the tutorial or the symposium or both. Visit the registration page.

Our Sponsors


Lexalytics logo

Open Text logo

Dow Jones logo


Attensity logo

NetBase logo

Anderson Analytics logo

Crimson Hexagon logo


Clarabridge logo

WiseWindow logo

SocialNuggets logo

Converseon logo