Feb 9, 2010
What is Sentiment Analysis and why you should care.
First let’s look at the definition of the Sentiment Analysis [Wikipedia]:
“Sentiment analysis or opinion mining refers to a broad (definitionally challenged) area of natural language processing, computational linguistics and text mining. Generally speaking, it aims to determine the attitude of a speaker or a writer with respect to some topic. The attitude may be their judgment or evaluation (see appraisal theory), their affective state (that is to say, the emotional state of the author when writing) or the intended emotional communication (that is to say, the emotional effect the author wishes to have on the reader).”
And why you should care?
Social Media and Social Networking have fueled the online space. Ratings, reviews, comments, etc – are everywhere. From NYT article http://www.nytimes.com/2009/08/24/technology/internet/24emotion.html :
“This is more than just an interesting programming exercise. For many businesses, online opinion has turned into a kind of virtual currency that can make or break a product in the marketplace.”
We tell our clients – you have to listen to what people are saying about your brand, products, services… and more importantly you should react, respond. Nicely said than done. Simple Twitter search on iPhone will give you tons of results. Is it possible for a brand to manually look at the every single mention and respond?? Of course not! Automation is the strategy… But – smart automation. As a consumer I do not want to get some irrelevant auto-response from a brand.
Solution – analysis of the unstructured texts. Not just on a set of keywords, but also on emotions. Not an easy task to do, but there are visionary companies who are working on tools/products that can help brands to deal with all these amounts of unstructured content and help them to make sense of the emotions hidden behind customer’s feedback.
We were able to gather an amazing panel of experts who will take us on a journey inside the fascinating space of sentiment analysis.
Save the date! You do not want to miss these discussions!
How Sentiment Analysis can Make Sense of Social Media (or Can it?)
Date: March 2, 2010
Location: Mountain View, CA
Time: 6:30 pm
Overview:
Ever since we realized that we needed more than mere transactional CRM data to get to know our customers and deliver on the mythical 360-degree view of them, we focused on two areas: what customers want (psychographics) and what customers feel (emotions and sentiments).
We spent the past 7-8 years figuring out direct and indirect feedback methods to try to understand what customers want and need using Enterprise Feedback Management and Surveys. We even went as far as to adopt and implement social media to capture the un-structured feedback that was latent in those interactions.
What we discovered along the way was that Social Media and unstructured feedback can be used to analyze sentiments and feelings, as customers are less controlled of their emotions when interacting in a social environment. We tried to understand the true sentiments behind the feedback and how we can use it for achieve our goals.
Alas, have we figured out how to use it and understand it? Can we really understand and use customers sentiments as metrics? What happens when we analyze for sentiments and not data? These are some of the questions we will aim to answer in this panel including:
· What is sentiment analysis?
· Does it work?
· What are the known problems?
· What are the know results?
· Should I implement it?
· What should I expect after implementation?
· What is the maintenance like?
· Is sentiment analysis for real?
· What are vendors doing about it?
Panelists:
Franco Salvetti holds a position as Senior SDE Manager of the Reference Vertical Answer team at Microsoft Bing Search (previously Natural Language Scientist at Powerset, Inc. now acquired by Microsoft) with responsibility on the scientific aspects related to Web Search Technologies (e.g., Factz and Instant Answers), and Human-Computer Interaction. Previously as a research scientist at Umbria Inc. (acquaried by J.D. Power) he worked on projects involving Information Extraction, Sentiment Analysis, Text Analysis and Graph Theory. Prior to this, he worked for Google in the area of Relation Extraction, IBM Research on a project about Social Network Analysis, Bioserve Space Technology and various start-up companies in Italy.
Jochen Frey is the CTO for Scout Labs and brings significant technical leadership and experience in scalable systems development and natural language processing to the organization. As CTO of Meaningful Machines for 5 years, Frey managed a combined onshore/offshore research and development team and deployed over $1mil in hardware to launch the world’s highest quality machine translation system (Spanish to English, with high quality prototypes for other languages including Arabic and French). He architected and oversaw implementation of high performance, failure tolerant message passing infrastructure and developed a high-speed 200GB distributed full text index. Prior to Meaningful Machines, Frey was the Director of Technology for the Eastern Region at Razorfish (previously iCube), architecting and overseeing numerous large-scale systems implementations. His past experience also includes software engineering for the US Navy and software design of risk management tools for Dresdner Bank in Frankfurt, Germany. Frey has his MS / Diplom Ingenieur in Computer Science and Medicine from the Ruprecht-Karls-Universität Heidelberg.
David Bean, PhD, Chief Technology Officer, Semantic Technologies, Attensity
In his role as CTO David is focused on the development of technologies that better manage and deliver superior natural language processing applications. David is the author/recipient of six patents and has over sixteen pending software patents. He is an Adjunct Assistant Professor in the University of Utah’s Linguistics Department, where he teaches applied computational linguistics. David is a sought-after guest lecturer to a wide range of commercial and academic groups. He is also passionate about lecturing at the elementary school level to introduce young minds to astronomy, physics and other cool science things. Prior to Attensity, David was an IS director and an independent consultant in the healthcare industry.
Esteban Kolsky is the Founder and Principal of ThinkJar LLC, a research and consulting organization focused on multi-channel Experience Management. He currently helps clients determine how to design, implement, and manage better experiences for communities and customers across all channels, including the new media and social channels. He also conducts research on SCRM and Communiities, which is distributed through his blog “CRM Intelligence and Strategies”.
Esteban has over 22 years of experience in the Customer Service and CRM space, spending more than ten of those years working as a consultant and advisor to some of the largest global organizations on their strategies for Customer Service, CRM and Experience Management. He also spent eight years at Gartner as an analyst writing about the future of CRM and CEM, including coining the concepts for Enterprise Feedback Management and Collaborative Customer Service, two of the hottest trends in social media.
