![](bg5.png)
Table 4: Precision, Recall and F-measure for Accuracy Test.
DA Events ADR Events
P% R% F% P% R% F%
DS1 93.3 93.3 93.3 98.1 97.8 97.8
DS2 91 90.4 90.4 97.1 96.8 96.8
DS3 84.7 83.3 83.9 96.6 95.6 95.8
Avg 89.7 89 89.2 97.3 96.7 96.8
ing SVM classifier to test accuracy of extracting drug
abuse events (DA) and adverse drug reactions (ADR).
We use three measures of accuracy; precision, re-
call and F-measure calculated based on the number of
positive instances, negative ones, false positives and
false negatives.
6 CONCLUSIONS
Social data generated in very high frequency require
real time analysis to make the quicker decision in
highly competitive environments. However, existing
technologies fail to process voluminous, unstructured
and dynamic data in real time and return required in-
formation for immediate decision making.
In this work, we adopt Hadoop, distributed frame-
work which offers a parallel programming model and
effective storage system in distributed clusters. Tested
on Twitter data for drug abuse events extraction,
Hadoop-based system achieved good performance re-
sults.
REFERENCES
Peotiuc-Pietro,D., Samangooei, S., Cohn, T., Gibbins, N.,
Niranjan, M. (2012). Trendminer: An Architecture
for Real Time Analysis of Social Media Text, Asso-
ciation for the Advancement of Artificial Intelligence
(www.aaai.org).
Nesi, P., Pantaleo, G., and Tenti, M. (2014).
Ge(o)Lo(cator): Geographic Information Extraction
from Unstructured Text Data and Web Documents.
DISIT - Distributed Systems and Internet Technol-
ogy Lab, Department of Information Engineering,
University of Florence, Italy.
Exner, P. and Nugues, P. (2014). KOSHIK- A Large-
scale Distributed Computing Framework for NLP,
ICPRAM2014-International Conference on Pattern
Recognition Applications and Methods
Ramesh, R., Divya, G., Divya, D., Kurian, M., Vish-
nuprabha, V. (2015). Big Data Sentiment Analysis us-
ing Hadoop, IJIRST International Journal for Innova-
tive Research in Science and Technology— Volume 1
— Issue 11 — April 2015, ISSN (online): 2349-6010
Ha, I., Back, B. and Ahn, B. (2015). MapReduce Functions
to Analyze Sentiment Information from Social Big
Data, Hindawi Publishing Corporation International
Journal of Distributed Sensor Networks Volume.
Dhamodaran, S., Sachin, K. R., and Kumar, R. (2015).
Big Data Implementation of Natural Disaster Mon-
itoring and Alerting System in Real Time Social
Network using Hadoop Technology, Indian Jour-
nal of Science and Technology, Vol 8(22), DOI:
10.17485/ijst/2015/v8i22/79102.
Sunil, B., Mane, B., Sawant, Y., Kazi, S., Shinde, V. (2014).
Real Time Sentiment Analysis of Twitter Data Us-
ing Hadoop International Journal of Computer Sci-
ence and Information Technologies, Vol. 5 (3) , 2014,
3098 3100
Prabhakar Benny, S., Vasavi, S., Anupriya, P. (2016).
Hadoop Framework For Entity Resolution Within
High Velocity Streams. International Conference on
Computational Modeling and Security (CMS 2016).
Procedia Computer Science 85(2016 )550 557.
Bharti, S. K., Vachha, B., Pradhan, R. K., Babu, K. S., Jena,
S. K. (2016). Sarcastic sentiment detection in tweets
streamed in real time: a big data approach. Digital
Communications and Networks 2, pp.108121
White, T., second edition, Hadoop: the definitive guide,
(2011) , Published by OReilly Media, Inc., 1005
Gravenstein Highway North, Sebastopol, CA 95472.
Jenhani F., Gouider M. S., Ben Said L. (2016) A Hybrid Ap-
proach for Drug Abuse Events Extraction from Twit-
ter In 20th International Conference on Knowledge-
Based and Intelligent Information and Engineering
Systems, (ICKIIES16) York, United Kingdom pp.
1032-1040.
Jenhani F., Gouider M. S., Ben Said L. (2016) Lexicon-
based System for Drug Abuse Entity Extraction from
Twitter In 12th International Conference, BDAS, Us-
tro, Poland, Beyond Databases, Architectures and
Structures. Advanced Technologies for Data Mining
and Knowledge Discovery, Volume 613 of the series.
Communications in Computer and Information Sci-
ence pp. 692-703.
Manning, D., Mihai, C., Bauer, S., Finkel, J., Bethard, J.,
McClosky, D. (2014). The Stanford CoreNLP Natural
Language Processing Toolkit.