Academia.edu no longer supports Internet Explorer.
To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to upgrade your browser.
Abstract. Determining the semantic relatedness (SR) of two terms has been an appealing topic in information retrieval for many years as such information is useful for various tasks ranging from tag recommendation, over search query refinement to suggesting new web resources for the user to discover. Most approaches consider the SR of terms as static over time, and disregard the eventual temporal changes as imperfections.
International Journal of Advanced Computer Science and Applications
Hashtag the Tweets: Experimental Evaluation of Semantic Relatedness Measures2016 •
Computational Intelligence and Neuroscience
Fast Distributed Dynamics of Semantic Networks via Social Media2015 •
We investigate thedynamicsof semantic organization using social media, a collective expression of human thought. We propose a novel, time-dependent semantic similarity measure (TSS), based on the social network Twitter. We show that TSS is consistent with static measures of similarity but provides high temporal resolution for the identification of real-world events and induced changes in the distributed structure of semantic relationships across the entire lexicon. Using TSS, we measured the evolution of a concept and its movement along the semantic neighborhood, driven by specific news/events. Finally, we showed that particular events may trigger a temporary reorganization of elements in the semantic network.
2020 •
As an online, crowd-sourced, open English-language slang dictionary, the Urban Dictionary platform contains a wealth of opinions, jokes, and definitions of terms, phrases, acronyms, and more. However, it is unclear exactly how activity on this platform relates to larger conversations happening elsewhere on the web, such as discussions on larger, more popular social media platforms. In this research, we study the temporal activity trends on Urban Dictionary and provide the first analysis of how this activity relates to content being discussed on a major social network: Twitter. By collecting the whole of Urban Dictionary, as well as a large sample of tweets over seven years, we explore the connections between the words and phrases that are defined and searched for on Urban Dictionary and the content that is talked about on Twitter. Through a series of cross-correlation calculations, we identify cases in which Urban Dictionary activity closely reflects the larger conversation happenin...
In the past, research has proposed that in order to process language in articles or human communications, computers require access to vast amounts of common sense and domain specific knowledge, just similar to what human would need to understand the content of articles to provide a topic or a summary. With the advent of Wikipedia, we find now a corpus of data where one can better classify a text or an article into a topic or mixed topics. We assume that pages on Wikipedia are very highly related to individual topics, with a topic being a thing, an event, a person, etc. We also assume that the level of interest in people’s conversations would relate to the level of interest for a topic, and we can connect topics based on whether the same group of people talk about the same topics, so if a golfer group collectively talk about both birdies and sand traps, we can assume there is a connection between those 2 topics. The contribution of this paper is threefold. First, we used word distributions to represent semantics of Tweets grouped in certain time frame, and we compute the semantic relatedness of Tweets to Wiki topics. Second, we used topic correlation to generate topic relatedness over time. Finally, we established the topic trend connection with the amount of Tweet activity topics over a span of 6 months and validate the accuracy of the generated trends by comparing it to search volume data from Google Trends.
2014 •
Online social media such as the micro-blogging site Twitter has become a rich source of real-time data on online human behaviors. Here we analyze the occurrence and co-occurrence frequency of keywords in user posts on Twitter. From the occurrence rate of major international brand names, we provide examples on predictions of brand-user behaviors. From the co-occurrence rates, we further analyze the user-perceived relationships between international brand names and construct the corresponding relationship networks. In general the user activity on Twitter is highly intermittent and we show that the occurrence rate of brand names forms a highly correlated time signal.
2012 •
In this paper we introduce an algorithmic approach, capable of creating a semantic network with concatenated terms and phrases (hash tags) from collectively postings on the Twitter sphere. This network could be exploited for query expansion provision in respect to users¢ information needs, without considering any other prior knowledge or access in search logs or browsing history records. For evaluation purposes, we compare our query expansion approach algorithm with query suggestions provided by well-known search ...
Proceedings of the Tenth …
Emerging topic detection on Twitter based on temporal and social terms evaluation2010 •
2023 •
The only eight Cimmerian time helmets which had been found in Ukraine as of now belong to three different types and have European analogies. Three of these helmets belong to the oldest type of metal helmets in Europe. There are two unique items, one probably being a transitional form between two subsequent types and another-the local imitation of foreign type. Generally, the presence of such findings in Ukraine indicate the lasting connections between peoples of the North Pontic Region and their western neighbors. The traces of damage on all eight helmets indicate their direct usage in combat.
This paper contains a selected collection of exams of geodesy and mathematical cartography. These exams are from the German school, namely from the Institute of Geodesy of the University of Stuttgart where the eminent professor Erik W. Grafarend (1939-2020) taught geodesy courses and in particular mathematical cartography. This is an opportunity for French-speaking students to share the German methodology.
Young Avestan pašne and its etymology. Acta Linguistica Petropolitana 18.1, 216–225
Young Avestan pašne and its etymology2022 •
Journal of Building Performance
Development of Energy Benchmarking of Malaysian Government Hospitals and Analysis of Energy Savings Opportunities2016 •
Editura pentru Literatură și Artă, București, 1959
Lucian din Samosata, Scrieri alese [tr. Radu Hîncu] [1959]Research Management Cell ,Bishwa Shanti Chiran-Millan Campus
A Report of International Conference 2024 On Peace and Security concerns of Nepal and Role of Nepali Diaspora Submitted to University Grants Commission Planning and Program Division Short-Term Capacity Development Program 2080 Sanothimi, Bhaktapur2024 •
Journal of the Academy for International Communication of Chinese Culture
Buddhism and Marxism: points of intersection2017 •
International Journal of Current Research in Medical Sciences
To compare efficacy of 10-day sequential triple therapy versus 14-days sequential therapy for the eradication of H. pylori2017 •
Educational Administration: Theory and Practice
The Cultural Contexts Of E-Learning In Higher Education In China And Flemish: A Study Focused Student And Teacher Perspectives2024 •
Experimental Astronomy
3D DIC tests of mirrors for the single-mirror small-size telescope of CTA2015 •
RAT, Humanistyka prewencyjna. Warszawa-Poznań: Muzeum Sztuki Nowoczesnej; Poznańskie Centrum Dziedzictwa
Wartość źródeł dźwiękowych dla wiedzy o przyszłości2022 •
Journal of physical education and sport
Improvement of Technical and Tactical Training of Qualified Women Epee Fencers2017 •
Revista Ecuatoriana de Ornitología
Nuevo Registro Altitudinal Del Pavón Nocturno Nothocrax Urumutum (Cracidae) y Notas Sobre Su Historia Natural2018 •
The Journal of neuroscience : the official journal of the Society for Neuroscience
Recurrent dendrodendritic inhibition of accessory olfactory bulb mitral cells requires activation of group I metabotropic glutamate receptors2007 •