Extracting fine‐grained location with temporal awareness in tweets: A two‐stage approach

Abstract

Twitter has attracted billions of users for life logging and sharing activities and opinions. In their tweets, users often reveal their location information and short‐term visiting histories or plans. Capturing user's short‐term activities could benefit many applications for providing the right context at the right time and location. In this paper we are interested in extracting locations mentioned in tweets at fine‐grained granularity, with temporal awareness. Specifically, we recognize the points‐of‐interest (POIs) mentioned in a tweet and predict whether the user has visited, is currently at, or will soon visit the mentioned POIs. A POI can be a restaurant, a shopping mall, a bookstore, or any other fine‐grained location. Our proposed framework, named TS‐Petar (Two‐Stage POI Extractor with Temporal Awareness), consists of two main components: a POI inventory and a two‐stage time‐aware POI tagger. The POI inventory is built by exploiting the crowd wisdom of the Foursquare community. It contains both POIs' formal names and their informal abbreviations, commonly observed in Foursquare check‐ins. The time‐aware POI tagger, based on the Conditional Random Field (CRF) model, is devised to disambiguate the POI mentions and to resolve their associated temporal awareness accordingly. Three sets of contextual features (linguistic, temporal, and inventory features) and two labeling schema features (OP and BILOU schemas) are explored for the time‐aware POI extraction task. Our empirical study shows that the subtask of POI disambiguation and the subtask of temporal awareness resolution call for different feature settings for best performance. We have also evaluated the proposed TS‐Petar against several strong baseline methods. The experimental results demonstrate that the two‐stage approach achieves the best accuracy and outperforms all baseline methods in terms of both effectiveness and efficiency.

A Survey on Deep Learning for Named Entity Recognition

“…This calls for more research in this area. In particular, we note that the performance of NER benefits significantly from the availability of auxiliary resources [177], [178], e.g., a dictionary of location names in user language. While Table 3 does not provide strong evidence of involving gazetteer as additional features leads to performance increase to NER in general domain, we consider auxiliary resources are often necessary to better understand user-generated content.…”

Face off: Travel Habits, Road Conditions and Traffic City Characteristics Bared Using Twitter

“…Gelernter and Balaji [27] have used a combination of gazetteer based location parser, a rule-based street/ building parser and a CRF-based recognizer to achieve better recall. Li et al [28], [29] observe that often user uses the abbreviation in place of the location name. Zhang et al [30] system rely on location mention recognizer they have proposed in previous study [31].…”

An Entity-Based Fine-Grained Geolocalization of User Generated Short Text

“…Lee et al [12] introduced Foursquare as a source for building the probabilistic models for locations using location-coupled words in tweets and then geocoded the non-geotagged tweets. Li et al [23] extracted PoI-level locations mentioned in tweets with temporal awareness. To formulate the PoIs' formal names and their informal abbreviations, they also introduced the crowd wisdom of the Foursquare community into the proposed method.…”