Search

Most trajectory pattern mining techniques assume that the data to be analyzed contain complete and evenly distributed spatial and temporal information. However in reality, collected data may contain noise, missing or incomplete information, and uneven spatial resolution. In trajectory pattern mining methods, trajectory patterns are extracted by splitting spatial workspace into uniformly tiny sized squares, followed by determining popular cells which contain many data points. Finally, a sequential pattern mining technique, e.g. MiSTA, is used to extract trajectory pattern. This research proposes non-uniform partitioning to handle uneven spatial distribution as modification towards the uniform spatial workspace division process. The proposed approach, named multistage spatial partitioning is developed based on point-region quadtree concept. The new partitioning method is conducted for preprocessing before applying MiSTA. As the result, using multistage spatial partition, MiSTA succeeds in uncovering more detailed and broader coverage patterns compared to uniform partitioning approach through a series of experiments. [ABSTRACT FROM AUTHOR]

Geoparser is a fundamental component of a Geographic Information Retrieval (GIR) geoparser, which performs toponym recognition, disambiguation, and geographic coordinate resolution from unstructured text domain. However, geoparsing of news articles which report several events across many place-mentions in the document are not yet adequately handled by regular geoparser, where the scope of resolution is either toponym-level or document-level. The capacity to detect multiple events and geolocate their true coordinates along with their numerical arguments is still missing from modern geoparsers, much less in Indonesian news corpora domain. We propose an event geoparser model with three stages of processing, which tightly integrates event extraction model into geoparsing and provides precise event-level resolution scope. The model casts the geotagging and event extraction as sequence labeling and uses LSTM-CRF inferencer equipped with features derived using Aggregated Topic Model from a large corpus to increase the generalizability. Throughout the proposed workflow and features, the geoparser is able to significantly improve the identification of pseudo-location entities, resulting in a 23.43% increase for weighted F1 score compared to baseline gazetteer and POS Tag features. As a side effect of event extraction, various numerical arguments are also extracted, and the output is easily projected to a rich choropleth map from a single news document. [ABSTRACT FROM AUTHOR]