Event detection on microposts: a comparison of four approaches
Microblogging services such as Twitter are important, up-to-date, and live sources of information on a multitude of topics and events. An increasing number of systems use such services to detect and analyze events in real-time as they unfold. In this context, we recently proposed ArmaTweet-a system...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
IEEE
2019
|
| _version_ | 1826288374195945472 |
|---|---|
| author | Bhardwaj, A Blarer, A Cudré-Mauroux, P Lenders, V Motik, B Tanner, A Tonon, A |
| author_facet | Bhardwaj, A Blarer, A Cudré-Mauroux, P Lenders, V Motik, B Tanner, A Tonon, A |
| author_sort | Bhardwaj, A |
| collection | OXFORD |
| description | Microblogging services such as Twitter are important, up-to-date, and live sources of information on a multitude of topics and events. An increasing number of systems use such services to detect and analyze events in real-time as they unfold. In this context, we recently proposed ArmaTweet-a system developed in collaboration among armasuisse and the Universities of Oxford and Fribourg to support semantic event detection on Twitter streams. Our experiments have shown that ArmaTweet is successful at detecting many complex events that cannot be detected by simple keyword-based search methods alone. Building up on this work, we explore in this paper several approaches for event detection on microposts. In particular, we describe and compare four different approaches based on keyword search (Plain-Seed-Query), information retrieval (Temporal Query Expansion), Word2Vec word embeddings (Embedding), and semantic retrieval (ArmaTweet). We provide an extensive empirical evaluation of these techniques using a benchmark dataset of about 200 million tweets on six event categories that we collected. While the performance of individual systems varies depending on the event category, our results show that ArmaTweet outperforms the other approaches on five out of six categories, and that a combined approach offers highest recall without adversely affecting precision of event detection. |
| first_indexed | 2024-03-07T02:12:43Z |
| format | Journal article |
| id | oxford-uuid:a13354f8-88da-442c-8d26-3f7815f838c5 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:12:43Z |
| publishDate | 2019 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:a13354f8-88da-442c-8d26-3f7815f838c52022-03-27T02:11:21ZEvent detection on microposts: a comparison of four approachesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:a13354f8-88da-442c-8d26-3f7815f838c5EnglishSymplectic Elements at OxfordIEEE2019Bhardwaj, ABlarer, ACudré-Mauroux, PLenders, VMotik, BTanner, ATonon, AMicroblogging services such as Twitter are important, up-to-date, and live sources of information on a multitude of topics and events. An increasing number of systems use such services to detect and analyze events in real-time as they unfold. In this context, we recently proposed ArmaTweet-a system developed in collaboration among armasuisse and the Universities of Oxford and Fribourg to support semantic event detection on Twitter streams. Our experiments have shown that ArmaTweet is successful at detecting many complex events that cannot be detected by simple keyword-based search methods alone. Building up on this work, we explore in this paper several approaches for event detection on microposts. In particular, we describe and compare four different approaches based on keyword search (Plain-Seed-Query), information retrieval (Temporal Query Expansion), Word2Vec word embeddings (Embedding), and semantic retrieval (ArmaTweet). We provide an extensive empirical evaluation of these techniques using a benchmark dataset of about 200 million tweets on six event categories that we collected. While the performance of individual systems varies depending on the event category, our results show that ArmaTweet outperforms the other approaches on five out of six categories, and that a combined approach offers highest recall without adversely affecting precision of event detection. |
| spellingShingle | Bhardwaj, A Blarer, A Cudré-Mauroux, P Lenders, V Motik, B Tanner, A Tonon, A Event detection on microposts: a comparison of four approaches |
| title | Event detection on microposts: a comparison of four approaches |
| title_full | Event detection on microposts: a comparison of four approaches |
| title_fullStr | Event detection on microposts: a comparison of four approaches |
| title_full_unstemmed | Event detection on microposts: a comparison of four approaches |
| title_short | Event detection on microposts: a comparison of four approaches |
| title_sort | event detection on microposts a comparison of four approaches |
| work_keys_str_mv | AT bhardwaja eventdetectiononmicropostsacomparisonoffourapproaches AT blarera eventdetectiononmicropostsacomparisonoffourapproaches AT cudremaurouxp eventdetectiononmicropostsacomparisonoffourapproaches AT lendersv eventdetectiononmicropostsacomparisonoffourapproaches AT motikb eventdetectiononmicropostsacomparisonoffourapproaches AT tannera eventdetectiononmicropostsacomparisonoffourapproaches AT tonona eventdetectiononmicropostsacomparisonoffourapproaches |