Geographical topic discovery and comparison
By Zhijun Yin, Liangliang Cao, Jiawei Han, Chengxiang Zhai, Thomas S. Huang. 2011
340 citations recorded by the source corpus.
Subfields: Geography, Planning and Development, Information Systems, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Geography, Planning and Development
In Information Systems
In Signal Processing
Citations in the corpus
- Is the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose (2013, background): “Finally, (Yin et al. 2011; Hong et al. 2012; Pozdnoukhov and Kaiser 2011) all study the problem of identifying topics in geographical Twitter datasets, proposing models to extract topics relevant to different geographical areas in the data.”
- Discovering regions of different functions in a city using human mobility and POIs (2012, background): “[18] study the distributions of some geographical topics (like beach, hiking, and sunset) in USA using geo-tagged photos acquired from Flickr.”
- Sampling Content from Online Social Networks (2015, methodology): “Note that topic models have been used by several prior studies to discover topics 2010; Yin et al. 2011].”
- Discovering geographical topics in the twitter stream (2012, background): “• Yin et al. [17]: Their method is essentially to have a global set of topics shared across all latent regions.”
- Towards social user profiling: unified and discriminative influence model for inferring home locations (2012, methodology): “In terms of expressiveness, either the heavy tailed distribution [4, 3] or the gaussian distribution [15, 19], which has been widely used for modeling probabilities over the geo space, can be used in our case.”
- Recommendations in location-based social networks: a survey (2015, background): “2011 [116] studied the distributions of some geographical topics (like beach, hiking, and sunset) from the geo-tagged photos acquired from Flickr.”
- Applications of Topic Models (2017, methodology): “Later work builds models location and topic jointly [Yin et al., 2011].”
- Regions, Periods, Activities: Uncovering Urban Dynamics via Cross-Modal Representation Learning (2017, methodology): “For CrossMap, we compute the average cosine similarity of each candidate location to the observed timestamp and keywords, and rank them in the descending order of the similarity; for LGTA and MGTM, we compute the likelihood of observing each candidate location given the keywords, and rank the candid”
- Geolocation Prediction in Social Media Data by Finding Location Indicative Words (2012, methodology): “, 2010), topic discovery (Yin et al., 2011), object matching (Dalvi et al.”
- Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey (2017, methodology): “To test their model, they gathered a dataset from the website Twitter and also we can say that, also can show from an author’s geographic location from raw text [139, 147, 184].”
- A location-based news article recommendation with explicit localized semantic analysis (2013, background): “The geographical context of a location can also be expressed as a topic vector, because most locations have their own geographical topics that are defined as spatially coherent meaningful themes [25].”
- Discovering Urban Functional Zones Using Latent Activity Trajectories (2015, background): “For example, [35] studied the distributions of some geographical topics (like the beach, hiking, and”
- SAR: A sentiment-aspect-region model for user preference analysis in geo-tagged reviews (2015, methodology): “Second, aspect and sentiment are usually modeled at sentence level [7] while region is modeled at the review or document level [5], [25], which makes it difficult to estimate the parameters of a unified model.”