Suchergebnisse

PUBLISHED ; An increasingly popular method of predicting trends and forecasting voting outcomes is to create a prediction model based on alignment of publicly available social media content produced by voters with voting behaviours. This paper aims to analyse whether Twitter data extracted from local Dublin City Council members' Twitter accounts in comparison with corresponding Councillor and Motion data from the Council- Tracker.ie website can be interpreted and used to create a model to predict the voting outcome of local Dublin City Council votes to pass motions. The aim was to explore whether through utilising machine learning techniques along with natural language processing techniques, reliable and data driven predictions can be generated for policy-making proposals brought forward. The acquired experimental results suggest that the approach used was marginally adequate in supporting the proposed hypothesis, although some interesting results were derived. Of the models analysed the Decision Tree model produced the most accurate results with an accuracy score of 0.71 (baseline: 0.63). Analysis of the models and an ablation study showed that the features derived from tweet texts and motion texts along with overall properties of a Councillor's twitter account were the most powerful indicators. The behaviour of a tweet, such as its acquired number of favorites or retweets, were not indicative of the results in both the random forest model and decision tree model

?The ultimatum game is a construct used to explore factors that influence decision making in economic reasoning. The game involves two players who asymmetrically encounter a windfall, but both knowing the amount of the windfall: one player proposes a division of the windfall between the two players; the other player either accepts the proposer?s suggested division, and in this case the windfall is divided between the players according to the proposal, even if the responder receives nothing, or the other player rejects the proposer?s offer, and in this case neither player receives anything. In this paper, influences on decisions to accept or reject offers within the ultimatum game (scale of windfall, wealth consciousness, and social proximity) are explored. Scale of windfall did not reveal an effect. Aspects of responders? socio-economic circumstances likely to associate with greater concern about finances, and therefore greater wealth consciousness, are shown to relate to a higher threshold for a minimum acceptable offer. Greater social distance between proposer and responder appears to increase rejection rates. These results demonstrate an influence of social and economic circumstances of participants on their economic reasoning.

PUBLISHED ; 22nd Italian Workshop on Neural Nets, WIRN 2012, May 17-19, Vietri sul Mare, Salerno, Italy. Springer Series: Smart Innovation, Systems and Technologies, Volume 19. ; Berlin ; Past research has demonstrated intercultural differences in emoticon use with effects of the topic of discourse (e.g. science vs. politics) interacting with the culture of online postings (e.g. UK, Italy, Sweden, Germany). The current research focuses within a discourse, and within a lingua franca for communication, and attempts to assess whether emoticon use varies as a function of user-type within the online context. The online context is a web user-forum associated with a software technology company. The user categories are determined by a few orthogonal classifications: employees, novice users, and experts; recipients of kudos vs. non-recipients of kudos; etc. As part of a developing theory of presentation of ``professional'' selves, and perceptions thereof, we test the hypotheses that kudo recipients deploy markedly fewer negative emoticons than comparison categories and that non-employee experts use markedly more emoticons in general than other categories of forum users. Also interactivity across the different group of users and their correlation with emoticon use was explored. ; SFI (Grant 07/CE/I1142)

Volltext // Exemplar mit der Signatur: München, Bayerische Staatsbibliothek -- Eur. 694 d-1239

PUBLISHED ; Best Paper Award ; Budapest, Hungary ; This paper is concerned with investigating conversational (verbal and non verbal) features related to conversational dominance and discovering evident relations between these features, personality traits and perceived dominance scores. Ordinal regression models were applied to find associations between dominance scores, both as a predicted value and as a predictor, and personality traits and verbal features. Results report the association of high dominance scores to the large number of words a speaker utters per minute, as well as to high extraversion and high openness traits. Low dominance scores have been associated with high agreeableness. ; European Union?s H2020 grant agreement No 701621 (MULTISIMO) Science Foundation Ireland (SFI) Grant 12/CE/I2267 and 13/RC/2106

1. Introduction -- 2. The Internet -- 3. Internet-Mediated Research: State of the Art -- 4. Sampling in Internet-Mediated Research -- 5. Ethics in Internet-Mediated Research -- 6. Tools and Design Strategies for Internet-Mediated Rsearch -- 7. What Can Go Wrong?

International audience ; This proposal outlines a plan for bridging the gap between technology experts and society in the domain of Artificial Intelligence (AI). The proposal focuses primarily on Natural Language Processing (NLP) technology, which is a major part of AI and offers the advantage of addressing problems that non-experts can understand. More precisely, the goal is to advance knowledge at the same time as opening new communication channels between experts and society, in a way which promotes non-expert participation in the conception of NLP technology. Such interactions can happen in the context of open-source development of languages resources, i.e. software tools and datasets; existing usages in various communities show how projects which are open to everyone can greatly benefit from the free participation of enthusiastic contributors (participation is not at all limited to software development). Because NLP research is mostly experimental and relies heavily on software tools and language datasets, this project proposes to interconnect the societal issues related to AI with the NLP research resources issue.

International audience ; This proposal outlines a plan for bridging the gap between technology experts and society in the domain of Artificial Intelligence (AI). The proposal focuses primarily on Natural Language Processing (NLP) technology, which is a major part of AI and offers the advantage of addressing problems that non-experts can understand. More precisely, the goal is to advance knowledge at the same time as opening new communication channels between experts and society, in a way which promotes non-expert participation in the conception of NLP technology. Such interactions can happen in the context of open-source development of languages resources, i.e. software tools and datasets; existing usages in various communities show how projects which are open to everyone can greatly benefit from the free participation of enthusiastic contributors (participation is not at all limited to software development). Because NLP research is mostly experimental and relies heavily on software tools and language datasets, this project proposes to interconnect the societal issues related to AI with the NLP research resources issue.

PUBLISHED ; Hefei, China ; Tasks and difficulties inherent in the largely open problem of temporal information extraction from legal text are outlined. We demonstrate the efficacy of tools and concepts available ?off-the-shelf? and suggest refinements for such applications. In particular, the frequent references between regulatory texts have to be addressed as a separate named entity recognition task that bears relevance to an analysis of the temporal ordering of legislation. A regular expression-based approach as a robust first step towards addressing this problem is tested. ; Enterprise Ireland: Governance Risk and Compliance Technology Centre Initial Grant CC-2011-2601-B.