Opinion Mining - Extraction of opinions from free text - Dataconomy

#artificialintelligence

There's a lot of buzz around the term "Sentiment Analysis" and the various ways of doing it. So you report with reasonable accuracies what the sentiment about a particular brand or product is. After publishing this report, your client comes back to you and says "Hey this is good. Now can you tell me ways in which I can convert the negative sentiments into positive sentiments?" – Sentiment Analysis stops there and we enter the realms of Opinion Mining. Opinion Mining is about having a deeper understanding of the review that was written.


How'd dinosaurs become birds?

FOX News

Scientists may have finally worked out how dinosaurs evolved into birds. Experts have isolated a genetic sequence which they believe was present in dinosaurs before and during their evolution into birds. Modern birds descended from a group of two-legged dinosaurs called theropods, whose members included the fearsome T-Rex and smaller Velociraptors. But identifying genomic DNA changes during this evolutionary transition has remained a challenge. Tohoku University researchers have isolated a gene sequence they believe was present in dinosaurs before and during their transition to the feathered creatures we recognise today.


Learning Latent Sentiment Scopes for Entity-Level Sentiment Analysis

AAAI Conferences

In this paper, we focus on the task of extracting named entities together with their associated sentiment information in a joint manner. Our key observation in such an entity-level sentiment analysis (a.k.a. targeted sentiment analysis) task is that there exists a sentiment scope within which each named entity is embedded, which largely decides the sentiment information associated with the entity. However, such sentiment scopes are typically not explicitly annotated in the data, and their lengths can be unbounded. Motivated by this, unlike traditional approaches that cast this problem as a simple sequence labeling task, we propose a novel approach that can explicitly model the latent sentiment scopes. Our experiments on the standard datasets demonstrate that our approach is able to achieve better results compared to existing approaches based on conventional conditional random fields (CRFs) and a more recent work based on neural networks.


Understanding Robocup-Soccer Narratives

AAAI Conferences

We present an approach to map Robocup-soccer narratives (in natural language) to a sequence of meaningful events. Our approach takes advantage of an action-centered framework, an inference subroutine, and an iterative learning algorithm. Our framework represents the narrative as a sequence of sentences and each sentence as a probability distribution over deterministic events. Our learning algorithm maps sentences to meaningful events without any annotated labeled data. Instead, it uses a prior knowledge about event descriptions and an inference subroutine to estimate initial training labels. The algorithm further improves the training labels at next iterations. In our experiments we demonstrate that with no labeled data our algorithm achieves higher accuracy compared to the state of the art that uses labeled data.


Transition-based Qualitative Simulation

AAAI Conferences

John M Gooday and Anthony G Cohn Artificial Intelligence Division School of Computer Studies University of Leeds Leeds LS2 9JT, UK {gooday,agc} @scs.leeds.ac.uk Abstract In this paper we present an event-based approach to qualitative simulation. We suggest that the behaviour of a system with time is best measured in terms of the landmark events that occur i.e. events that result in interesting changes to the system being modelled. For us, a behaviour model corresponds not to a sequence of qualitative state descriptions but to a set of event sequences -- the things that actually happen to the system rather than the way it happens to be at certain times. Although we have a simple implementation of our system, our primary purpose in developing it is to derive a high level, event-based, nonmonotonic language for specifying qualitative simulation systems. We not only illustrate how a qualitative simulation program can be directly specified (and implemented) in our language, we also sketch how qualitative simulation systems from the literature can be defined and reconstructed in our calculus. Introduction Qualitative simulation is a well-established artificial intelligence technique for modelling and predicting the behaviour of physical systems. Programs such as QSIM (Kuipers 1994) derive behaviour models from an initial qualitative description of a system and a set of constraints that specify how individual parameter values within the system might change. By varying system parameters in accordance with the-constraints, a sequence of time-ordered snapshots (or qualitative states) can be generated. The set of all possible such sequences (or histories) forms the complete behaviour tree of the system being modelled.