Colm O’Riordan

Exploiting Wikipedia for Entity Name Disambiguation in Tweets

Social media repositories serve as a significant source of evidence when extracting information related to the reputation of a particular entity (e.g., a particular politician, singer or company). Reputation management experts are in need of automated methods for mining the social media repositories (in particular Twitter) to monitor the reputation of a particular entity. A quite significant research challenge related to the above issue is to disambiguate tweets with respect to entity names. To address this issue in this paper we use “context phrases” in a tweet and Wikipedia disambiguated articles for a particular entity in a random forest classifier. Furthermore, we also utilize the concept of “relatedness” between tweet and entity using the Wikipedia category-article structure that captures the amount of discussion present inside a tweet related to an entity. The experimental evaluations show a significant improvement over the baseline and comparable performance with other systems representing strong performance given that we restrict ourselves to features extracted from Wikipedia.

Evolving Strategies for Agents in the Iterated Prisoner’s Dilemma in Noisy Environments

In this paper, we discuss the co-evolution of agents in a multi-agent system where agents interact with each other. These interactions are modelled in an abstract manner using ideas from game theory. This paper focuses on the iterated prisoner’s dilemma (IPD). We discuss properties that we believe to be of importance with respect to fitness of strategies in traditional environments and also in environments where noise is present. Specifically, we discuss the notion of forgiveness, where strategies attempt to forgive strategies that defect in the game, with the aim of increasing the level of cooperation present. We study these strategies by using evolutionary computation which provides a powerful means to search the large range of strategies’ features.

Clustering with Error-Estimation for Monitoring Reputation of Companies on Twitter

The aim of this research is to easily monitor the reputation of a company in the Twittersphere. We propose a strategy that organizes a stream of tweets into different clusters based on the tweets’ topics. Furthermore, the obtained clusters are assigned into different priority levels. A cluster with high priority represents a topic which may affect the reputation of a company, and that consequently deserves immediate attention. The evaluation results show that our method is competitive even though the method does not make use of any external knowledge resource.

Utilizing Microblog Data in a Topic Modelling Framework for Scientific Articles’ Recommendation

Researchers are actively turning to Twitter in an attempt to network with other researchers, and stay updated with respect to various scientific breakthroughs. Young and novice researchers have also found Twitter as a valuable source of information in terms of staying up-to-date with various developments in their field of research. In this paper, we present an approach to utilize this valuable information source within a topic modeling framework to suggest scientific articles of interest to novice researchers. The approach in addition to producing effective recommendations for scientific articles alleviates the cold-start problem and is a step towards elimination of the gap between Twitter and science.

Providing Personalised Recommendations in a Web-Based Education System

Given the changing profile of learners, the continual need to enhance employee skills and the flexibility offered by online learning, web-based education has been afforded much attention in the past number of years. It is imperative that web-based education provides personalised learning (right information to the right people) and also addresses the feelings of isolation reported by many students who are learning without the traditional classroom environment. This paper presents details of a system which provides personalised intelligent recommendations on course content and peer-peer groups. We present an approach to combine different sources of information by utilising a number of approaches including information retrieval and collaborative filtering techniques.

Spatial N-player Dilemmas in Changing Environments

In recent work it has been shown that, given the presence of a community structure in a population of agents, cooperation can be a robust outcome for agents participating in an N-player social dilemma. Through the use of simple imitative learning, cooperation can spread and be the dominant robust behaviour. In this paper, we show that such cooperation can exist in the presence of noise and that persistent small levels of noise can allow the population to adapt suitably to dramatic changes in the environment.

A further analysis of the role of heterogeneity in coevolutionary spatial games

This work was supported by the National Council for Scientific and Technological Development (CNPq-Brazil) Grantnumber: 234913/2014-2

Measuring diversity in populations employing cultural learning in dynamic environments

This paper examines the effect of cultural learning on a population of neural networks. We compare the genotypic and phenotypic diversity of populations employing only population learning and of populations using both population and cultural learning in two types of dynamic environment: one where a single change occurs and one where changes are more frequent. We show that cultural learning is capable of achieving higher fitness levels and maintains a higher level of genotypic and phenotypic diversity.

Evolving Blackjack Strategies Using Cultural Learning

This paper presents a new approach to the evolution of blackjack strategies, that of cultural learning. Populations of neural network agents are evolved using a genetic algorithm and at each generation the best performing agents are selected as teachers. Cultural learning is implemented through a hidden layer in each teacher’s neural network that is used to produce utterances which are imitated by its pupils during many games of blackjack. Results show that the cultural learning approach outperforms previous work and equals the best known non-card counting human approaches.

Cultural Evolution for Sequential Decision Tasks: Evolving Tic–Tac–Toe Players in Multi–agent Systems

Sequential decision tasks represent a difficult class of problem where perfect solutions are often not available in advance. This paper presents a set of experiments involving populations of agents that evolve to play games of tic–tac–toe. The focus of the paper is to propose that cultural learning, i.e. the passing of information from one generation to the next by non–genetic means, is a better approach than population learning alone, i.e. the purely genetic evolution of agents. Population learning is implemented using genetic algorithms that evolve agents containing a neural network capable of playing games of tic–tac–toe. Cultural learning is introduced by allowing highly fit agents to teach the population, thus improving performance. We show via experimentation that agents employing cultural learning are better suited to solving a sequential decision task (in this case tic–tac–toe) than systems using population learning alone.