Group items tagged

Sentiment analysis is a tricky thing. Even humans disagree on sentiment 15 percent of the time, so how can a computer create something more accurate?

SentiStrength estimates the strength of positive and negative sentiment in short texts, even for informal language. It has human-level accuracy for short social web texts in English, except political texts. SentiStrength reports two sentiment strengths: -1 (not negative) to -5 (extremely negative) 1 (not positive) to 5 (extremely positive) It can also report binary (positive/negative), trinary (positive/negative/neutral) and single scale (-4 to +4) results. SentiStrength was originally developed for English and optimised for general short social web texts but can be easily configured for other languages and contexts by changing its input files - some variants are demonstrated below.

Sentiment analysis based on customised, ontology-based machine-learning, delivering testable data. No pre-defined list of sites, no pre-defined off the shelf analytics tools. i-sieve is different.

A detailed case study of commuting and social networks in San Jose, which suggests that sentiment analysis has the potential to help cities and local transportation authorities define their priorities, planning, investments and assess the impact of infrastructure investments.

Austria , Germany , Greece , Switzerland , United Kingdom Type of initiative Project or service Case Abstract NOMAD aims to introduce the experience of setting a political agenda in a non-moderated, crowd sourcing way, by providing decision-makers with automated solutions for content search, acquisition, analysis and visualisation, while gathering online information from social media, blogs, news feeds and the web, following upon complex sets of issues.

core technology consists of: real-time content aggregation a four-step spam filtering process an accurate sentiment engine robust geo-demographic information sophisticated text analytics and language processing algorithms

In today's hyper-connected world, social media and online customer interactions are changing the way companies do business from the outside in. Leading brands recognize that their customers are both passionate and vocal about their products and services, and they are sharing their experiences in conversations every day. Until recently, however, social monitoring tools allowed you to listen to these conversations, but lacked the sophisticated analytics capabilities needed to derive critical business insights. Attensity enables you to go beyond mere social media monitoring to: LISTEN to social customer conversations from over 75 million online sources, including the full Twitter Firehose, Facebook, blogs, communities, forums and other sources. ANALYZE those conversations for key business insights, going beyond basic sentiment to get detailed reports on customer feedback about new products, campaigns, brands, service and support, and other business drivers. RELATE that intelligence to structured data within your existing customer systems such as CRM, ERP, BI, EFM and other systems. ACT with a Playbook that allows you to take charge of emerging issues and manage the customer experience based on your own organizational structure and business processes.

Clarabridge provides individual departments, Global 1000 enterprises and technology and service providers with an universal view of their customers through transforming of text-based verbatim into customer experience insight. Clarabridge collects all sources of customer feedback, transforms it using Natural Language Processing (NLP), categorizes the content, performs sentiment scoring and delivers customer insights enterprise-wide though a variety of interfaces.