Doctoral Forum and External Speakers 2016-17
We hold an approximately monthly (every second Tuesday) series of doctoral forums for Webometrics in Wolverhampton that is aimed mainly at the Wolverhampton cybermetrics team, but is open to related researchers who are would like to participate - please email any member of the team to get an invitation. At each forum, we alll talk briefly about our current or planned research and get feedback from others.
2007/8 Meeting at 12 for lunch outside the library main entrance, then discussions 1-3.
- Monday/Tuesday 11-12 September Web indicators summer school.
- Tuesday 10 October at 12 outside the MD library, then discussion in MC238
- Tuesday 14 November at 12 outside the MD library, then discussions in room MC414
- Tuesday 12 December at 12 outside the MD library, then discussions in room MC406. End of year evening dinner at 6.30pm Tuesday 12 December at Mystic Grill Dosa, 25 Market Street, Wolverhampton.
- Tuesday 9 January 2018 at 12 outside the MD library, then discussions in room MC227
- Tuesday **6** February 2018 at 12 outside the MD library, then discussions in room MC232.
- Wednesday 7 February 2018 1-2pm: Talk by Thaiane Oliveira, Universidade Federal Fluminense (UFF), Brazil. Room MC225: Brazilian policies and geopolitics in the knowledge era: An analysis of the global scientific ecosystem
- Tuesday 13 March 2018 at 12 outside the MD library, then discussions in room TBA
- Monday 19 March 2018 at 12 outside the MD library for lunch, then talk by Reshmi Pillai in MU402. *New
- Detection of strength and causal agents of stress and relaxation in social media content
Hypothesis: The accuracy of a person’s psychological stress and relaxation magnitude measurement from his social media content can be improved by incorporating word sense disambiguation. The causal agents of stress and relaxation can be inferred from the social media output.
Research Questions: Can the accuracy of psychological stress or relaxation strength detection from social media content be improved using word sense disambiguation? Can the Aspect Based Sentiment Analysis methods to detect keywords in tweets be used for identifying causal agents of stress and relaxation from social media content?
- Friday 23 March 2018 in MC225. Title: Unsupervised Citation Sentence Identification based on Similarity Measurement
Speaker: Dr. Shiyan Ou, School of Information Management, Nanjing University, China
Abstract: Citation Context Analysis has obtained the interest of many researchers in the field of bibliometrics. To do this, the first step is to extract the context of each citation from a citing paper. We proposed a novel unsupervised approach for the identification of implicit citation sentences without attaching a citation tag. Our approach selects the neighboring sentences around an explicit citation sentence as candidate sentences, calculates the similarity between a candidate sentence and a cited or citing paper, and deems those that are more similar to the cited paper to be implicit citation sentences. To calculate text similarity, we proposed four methods based on the Doc2vec model, the Vector Space Model (VSM) and the LDA model respectively. The experiment results showed that the hybrid method combing the probabilistic TF-IDF weighted VSM with the TF-IDF weighted Doc2vec obtained the best performance. Compared against other supervised methods, our approach does not need any annotated training corpus, and thus can be easy to apply to other domains in theory.
- Tuesday 10 April 2018 at 12 outside the MD library, then discussions in room TBA
- Tuesday 8 May 2018 at 12 outside the MD library, then discussions in room TBA
- Tuesday 12 June 2018 at 12 outside the MD library, then discussions in room TBA
- Tuesday 10 July 2018 at 12 outside the MD library, then discussions in room TBA
- Thursday-Friday 6/7 September 2018: Alternative Indicators Summer School 2018