=Paper=
{{Paper
|id=Vol-2077/paper1
|storemode=property
|title=IREvent2Story: A Novel Mediation Ontology and Narrative Generation
|pdfUrl=https://ceur-ws.org/Vol-2077/paper1.pdf
|volume=Vol-2077
|authors=Venumadhav Kattagoni,Navjyoti Singh
|dblpUrl=https://dblp.org/rec/conf/ecir/KattagoniS18
}}
==IREvent2Story: A Novel Mediation Ontology and Narrative Generation==
https://ceur-ws.org/Vol-2077/paper1.pdf
IREvent2Story: A Novel Mediation Ontology and
Narrative Generation
VenuMadhav Kattagoni Navjyoti Singh
Center for Exact Humanities Center for Exact Humanities
IIIT Hyderabad IIIT Hyderabad
venumadhav.katagoni@gmail.com singh.navjyoti@gmail.com
Abstract
Event detection is a key aspect of story development which is composed
of multiple narrative layers. Most of the narratives are template-based
and follow a narration theory. In this paper, we demonstrate a narra-
tive from events detected in the international relations domain along
with classification of events using our novel mediation ontology. We
also introduce a novel method of classifying events through the medi-
ation ontology. Our methodology involves action classification based
on the verb categorization of Beth Levin, its arguments determined
by universal dependencies and word2vec. The selected feature space
is a result of mapping language entities to ontological entities where
we obtain substantially good results. The narration also presents in-
teractions of international actors over various topics as well as other
visualizations.
1 Introduction
[GP12] states that “The field of international relations concerns the relationships among the world’s govern-
ments. But these relationships cannot be understood in isolation. They are closely connected with other actors
(such as international organizations, multinational corporations, and individuals); with other social structures
and processes (including economics, culture, and domestic politics); and with geographical and historical influ-
ences. These elements together power the central trend in international relations today — globalization”. Actors
[Kan09] in international relations include individuals, groups (including ephemeral groups like crowds), organi-
zations(including corporate entities, both public and private) and all generally recognized countries (including
states and related territories). Classification of the events detected is important so as to analyze the group as a
whole rather than each event discretely. Thus, we propose a new Mediation Ontology for international relations.
This new mediation ontology provides a correlation between language entities and ontological entities which is
used for classification of events into the proposed categories. We use its result as one of the visualizations in the
narration.
We present a brief background on event ontologies and event coding in conjunction with media in Section
2. Our new Mediation Ontology is presented in Section 3. We then write about our dataset in Section 4. In
Section 5, our methodology and results for classification of events to identify the event type and description of
Copyright c 2018 for the individual papers by the paper’s authors. Copying permitted for private and academic purposes. This
volume is published and copyrighted by its editors.
In: A. Jorge, R. Campos, A. Jatowt, S. Nunes (eds.): Proceedings of the Text2StoryIR’18 Workshop, Grenoble, France, 26-March-
2018, published at http://ceur-ws.org
the features used along with machine learning techniques for classification are discussed. In subsequent sections,
narratives and visualizations are demonstrated in section 6 with a case study. We conclude the paper in section
7 with proposals on the future work sparked by this study.
2 Related Work
The last few decades have witnessed a considerable escalation in studies which are directed at event coding
ontologies in the political domain. This kind of research began during the 1970s with the purpose of forecasting
international conflict under the sponsorship of the U.S. Department of Defense Advanced Research Projects
Agency (DARPA) [CR78], [AH88]. The kind of research that has been focused is mainly on:
1. the political event data coding ontologies.
2. the generation of the political event data.
3. forecasting of international conflict.
Our focus in this paper is restricted to international relations event coding ontology i.e., Ontology for interna-
tional relations events or mediation types. Such ontologies include WEIS [Gol92], COPDAB [Aza80], CAMEO
[GSYAJ02], IDEA [BBO+ 03] etc. The WEIS Ontology is made up of 22 top-level categories that encompass
actions such as Request or Grant. Each of these 22 top-level categories contain single level children which are
further fine-grained. For example, the code 07 is the top-level code for reward with the sub-code 072 representing
extended military assistance. The CAMEO ontology is an upgraded version of WEIS with mediation event types
added to it. It is more fine-grained with 20 top-level categories that encompass actions such as Make-Statement
or Protest. Each of these 20 top-level categories contain finer-grained categories in a hierarchical manner. For
example, the code 14 is the top-level code for Protest with the sub-code 141 representing a general demonstration
or rally. Under the code 141 is code 1411 which codes demonstrate or rally for leadership change. Thus, as one
moves down the hierarchy of CAMEO, it becomes concise. Based on one’s need, CAMEO or any event data
coding schemes can be evolved using a mix-and-match framework whereby a researcher could adopt most of his
or her coding categories from a standard set, and then elaborate on a smaller number of newer categories. Event
coding using CAMEO [GSYAJ02] involves event detection and classification based on pattern matching from
a large set of verb patterns, actors, compound nouns, compound verb phrases, reference to pronouns and deep
parsing of sentences in news articles. Prior to CAMEO [GSYAJ02], event encoding was done manually based on
the rules mentioned in the corresponding codebooks. Our work presented in this paper carves a similar problem
by computing event types and narrative generation of the international events.
3 Mediation Ontology
Bercovitch [Ber97] defines mediation as “a process of conflict management, related to but distinct from the
parties’ own negotiations, where those in conflict seek the assistance of, or accept an offer of help from, an
outsider (whether an individual, an organization, a group, or a state) to change their perceptions or behaviour,
and do so without resorting to physical force or invoking the authority of law.” He also mentions, “Mediation may
well be the closest thing we have to an effective technique for dealing with conflicts in the twenty-first century”.
The main goals of this research are event classification and narrative generation so as to help journalists and
researchers identify interactions among actors during international conflicts.
Our mediation ontology is inspired from social agents grouped under “The ontologies of Persons” mentioned
by [Bic12]. He mentions, “Persons, so I argue, are special kinds of agents that arise in and are constituted
in interactions with social and cultural processes, including other social persons, and thereby co-constitute the
emergence base for those social and cultural realities.” He adds that “In this model, agents are constituted
in their interactive dynamics; such interactive dynamics is their ontology.” Our mediation ontology is inspired
from this concept of person and interactive dynamics. He also states that “Agents that develop to become
participants, thus constitutive participants, in those environments are themselves, therefore, emergent kinds of
agents — social agents:persons.” A person’s interactive dynamics can be inferred from the pronouncements he
makes, the engagements he has with other persons, his response to another person’s opinions and the use of
force in unhealthy relations. In a similar manner, an actor in international relations interacts with other actors
through pronouncements, engagements, responses and force mechanisms. The responses and force mechanisms
of an actor determine the pronouncements and engagements made by peers. This is because pronouncements and
Figure 1: Mediation Ontology
engagements happen only when some kind of base event has occurred. Hence, force mechanisms and responses
are ground event types whereas pronouncements and engagements are lateral event types. As mentioned by
[GP12], the relations among the actors is what the field of international relations is concerned about. Therefore,
multiple actors coming together would determine international relations.
The motivation behind a new mediation ontology arises from the 250+ classes in CAMEO [GSYAJ02]. There
is an overlap in the mappings from verbs to classes in their verb dictionaries. Also, verb classification is an
extremely context-sensitive exercise. Hence, we map language entities with ontological entities while proposing a
new statistical model of event classification system which meets all our requirements. We classified an event type
into four classes instead of the 20 top-level classes that CAMEO [GSYAJ02] consists of (with nearly 250+ sub-
classes). Since CAMEO [GSYAJ02] is widely used, we mapped the CAMEO [GSYAJ02] categories as following
in order to come-up with the current definitions of event types.
1. Pronouncements
- Declining to comment, making pessimistic and optimistic comment, claiming, denying, empathetic, accord,
symbolic act, policy option.
- Appeal for material or diplomatic cooperation, aid, political reform, negotiation, settling disputes, accept-
ing mediation.
- Expressing intent to cooperate, material or diplomatic cooperation, providing aid, political reform, yield,
negotiating, settle disputes, mediation.
- CAMEO Classes - 01, 02, 03.
2. Engage
- Consult, discuss, meet, negotiate, mediate.
- Engaging in diplomatic, material, economic, military, judicial, intelligence cooperation, endorse, defend
verbally, support, recognize, apologize, forgive, formal agreement.
Code Class Name
01 Make Public System
02 Appeal
03 Express intent to cooperate
04 Consult
05 Engage in Diplomatic Cooperation
06 Engage in Material Cooperation
07 Provide Aid
08 Yield
09 Investigate
10 Demand
11 Disapprove
12 Reject
13 Threaten
14 Protest
15 Exhibit Force Posture
16 Reduce Relation
17 Coerce
18 Assault
19 Fight
20 Use unconventional mass violence
Table 1: CAMEO’s top-level classification
Class Training Data Testing Data Total
Pronouncements 38130 4237 42367
Engage 23136 2571 25707
Respond 16275 1809 18084
Force 15510 1724 17234
Total 93051 10341 103392
Table 2: Dataset Description
- CAMEO Classes - 04, 05, 06, 07.
3. Respond
- Any type of response in the form of yield, investigate, demand, disapprove, reject, threaten, protest.
- CAMEO Classes - 08, 09, 10, 11, 12, 13, 14
4. Force
- Any type of force posture, reducing relations, coerce, assault, fight, use unconventional mass violence.
- CAMEO Classes - 15, 16, 17, 18, 19, 20
Our mediation ontology is described in figure 1. All the 20 top-level CAMEO classes are described in table
1.
4 Dataset
Our system listens to 248 media feeds1 for news articles daily. We use the methodology proposed in [KS18] to
extract events between September 1, 2017 and September 30, 2017. Since we mapped our categorical information
with CAMEO, we used the Petrarch system [CN17] based on CAMEO [GSYAJ02] to generate its event types
and map to our categories. We generated a total of 103392 events distributed across all the four classes. Detailed
description regarding our dataset is described in table 2.
1 http://ceh.iiit.ac.in/international relations/source.txt
Figure 2: Methodology.
5 Methodology and Results
The methodology is described in figure 2. The sentence in which the event is detected is sent to Stanford
Dependency parser[CM14] to identify the action verb and its dependencies. The identified action verb, its
arguments and universal dependency relations [NdMG+ 16] are passed through 3 different modules which finally
unite to form our feature space.
1. In the first module, we identify the class of the verb with respect to Beth Levin Verb Classes [Lev93] consid-
ering verb and its alternations in the sentence. We chose 59 classes which are relevant to our classification.
Mapping between Beth Levin [Lev93] Verb Classes and our mediation ontology categories is described in
table 3.
2. In the second module, the verb and its arguments which are found using the universal dependencies are
converted to vectors using Google word2vec pretrained model [TMS]. All the argument vectors are added
to the verb vector.
3. In the third module, all the universal dependency relations [NdMG+ 16] of the verb with its arguments are
taken into account. Since, there are 40 universal dependencies as mentioned in [NdMG+ 16], we consider a
40 dimensional vector which is normalized by the total number of dependencies detected in the sentence.
The results of a few Machine Learning algorithms (viz., Logistic Regression, Random Forest, ensemble of
Logistic Regression and Random Forest and Multi-Layer Perceptron) on the feature space obtained from the
Class Beth Levin Verb Classes
Pronouncements Characterize Verbs , Appeal Verbs , Long Verbs , Verbs of Transfer of a Message , Tell
Verbs, Verbs of Manner of Speaking , Say Verbs , Complain Verbs , Reflexive Verbs of
Appearance
Engage Pit Verbs , Drive Verbs , Contribute Verbs , Verbs of Future Having , Verbs of Exchange
, Build Verbs , Grow Verbs , Create Verbs , Performance Verbs , Dub Verbs , Conjecture
Verbs , Admire Verbs , Judgment Verbs , Correspond Verbs , Meet Verbs , Talk Verbs
, Chitchat Verbs , Dine Verbs , Gorge Verbs , Verbs of Spatial Configuration , Verbs of
Contiguous Location , Verbs of Inherently Directed Motion , Roll Verbs , Verbs that are
not Vehicle Names , Accompany Verbs
Respond Banish Verbs , Manner Subclass , Verbs of Possessional Deprivation: Cheat Verbs , Get
Verbs , Hold Verbs , Verbs of Concealment , Separate Verbs , Split Verbs , Disassemble
Verbs , Amuse Verbs , Verbs of Assessment , Search Verbs , Investigate Verbs , Advise
Verbs , Break Verbs , Bend Verbs , Other Alternating Verbs of Change of State , Verbs of
Lingering
Force Throw Verbs , Hit Verbs , Swat Verbs , Sight Verbs , Murder Verbs
Table 3: Mapping between Mediation categories and Beth Levin Classes.
Method (One Vs Rest Classifier) Precision Recall F1-Score Accuracy
Logistic Regression 0.79 0.80 0.79 0.78
Random Forest 0.75 0.77 0.76 0.73
Ensemble (Logistic Regression + Random Forest) 0.78 0.80 0.79 0.77
Multi-layer Perceptron 0.80 0.80 0.80 0.80
Table 4: Results
above methodology are described in the table 4. The ensemble technique we used is majority rule voting. All
the hyper-parameters of Multi-Layer Perceptron [HM94] are described in table 5. All the metrics (precision,
recall and accuracy) are the average of the corresponding class metrics. The optimum result was obtained using
Multi-Layer Perceptron [HM94] with precision, recall and accuracy of 80%. The results are favourable using
Multi-Layer Perceptron [HM94] because of the backpropagation training algorithm. It is worth to note that all
the other Machine Learning algorithms produce nearly same results which gives a strong base for the choice of
our feature space.
6 Narrative Generation
We use the event model presented by [KS18] for extracting events with attributes date-time, location, actors,
media-source, event-title, source-url, sentence. Extending this model with action (verb) and action-type (event-
type), our mediation ontology adds two new attributes — action and action-type. These attributes capture
individual actions when events are grouped with topics helping in capturing subtler details of the generated
narrative. Updated event model is shown in figure 3.
Our system visualizes the event actor interaction using graphical, topical, geographical and temporal features.
These visualizations help journalists and researchers in IR domain in understanding the interactions among
actors.
Hyper-Parameter Congifured Description
Hidden layer sizes (100,)
Activation function for hidden layer Rectified linear unit function
Solver adam (Stochastic gradient-based optimizer proposed by [KB14])
Learning Rate Constant with an initial learning rate of 0.001
Maximum number of iterations until 200
solver converges
Tolerance for optimization 0.001
Table 5: Hyper-parameters of Multi-Layer Perceptron
Figure 3: Updated Event Model with action and action-type attributes added.
We consider the definition of narrative event chain by [CJ08]. [CJ08] states that “A narrative event is a tuple
of an event and its participants, represented as typed dependencies. A narrative event chain is a partially ordered
set of narrative events that share a common actor (protagonist).” Our narrative event chain is also a partially
ordered set of narrative events that shares two common actors.
The narrative starts with the description of two actors followed by various visualizations describing the inter-
action of the actors.
1. Bar Chart: The bar chart depicts frequency of the events reported involving both the actors with the most
reported topics of interaction and unique events.
2. Line Chart: The line chart compares the frequency of the events reported involving individual and com-
bined actors. This provides how important the interaction of the mentioned actors is in comparison to total
number of interactions reported with all other actors.
3. Mediation Class Events: The mediation class events gives the number of events reported in each category
of the mediation ontology. This visualization provides comparison among the classes of interaction.
4. Graph Visualization: The graphical visualization represents the interaction wherein nodes are the actors
and the edges are topics of interaction. This visualization helps place an actor level context to the conflict.
Hovering on the nodes and edges provides with the actor name and the topics of interaction respectively.
5. Topic Cloud: The topical visualization helps situate the gravity of the topics spoken of and thus giving a
subjective view of the conflict. It is created based on the frequency of the words used in the topic.
6. Geographic Visualization: The geographical visualization brings to the fore the narrative about actor’s
stakes in the international conflict and thus add a geopolitical persona to the event. The importance of the
actor increases with the increase in the number of sub-actors. Hovering on the circle gives all the actors and
sub-actors involved in that area.
7. Timeline Visualization: The timeline visualization helps bring a coherency to the event-actor duo and
places the interaction over a span of the dialogue until its closure.
We show an example of a narrative involving Japan and South Korea as common actors surrounded by a
narrative event chain. All the narrative visualizations between them are shown in figure 4.
A live prototype of the system is available here: http://ceh.iiit.ac.in/international_politics/
(a) Bar Chart
(b) Line Chart (c) Graph Visualization
(d) Mediation Class Counts
(e) Topic Visualization (f) Map Visualization
Figure 4: All visualizations in the narrative.
(g) Timeline Visualization
Figure 4: All visualizations in the narrative (cont.)
7 Conclusion and Future Work
Our paper described a novel ontology for categorization of the news events which helps in event classification in
the international relations. We built a system, IREvent2Story that helps identify the various narrative features
behind the events. Our ontology is a step towards framing a further attuned vocabulary for discussion of any
international exchange thus setting the base for more theory work on ideating a framework for mapping not only
political entities but also include non-political entities in a similar framework. Our ontology helps to not only
drive meaning through the vast news data corpus but also acts as a step towards conceptualizing self-hydrating
and sustaining systems of data journalism that will usher with the Web 2.0. The vision of this research is also
to find the parts in the news article where the conflict is framed and compare this conflict among various news
sources.
References
[AH88] Stephen J Andriole and Gerald W Hopple. Defense Applications of Artificial Intelligence. Lexington
Books, 1988.
[Aza80] Edward E. Azar. The conflict and peace data bank (copdab) project. Journal of Conflict Resolution,
24(1):143–152, 1980.
[BBO+ 03] Doug Bond, Joe Bond, Churl Oh, J. Craig Jenkins, and Charles Lewis Taylor. Integrated data for
events analysis (idea): An event typology for automated events data development. Journal of Peace
Research, 40(6):733–745, 2003.
[Ber97] Jacob Bercovitch. Mediation in international conflict: An overview of theory, a review of practice.
Peacemaking in international conflict: Methods and techniques, pages 125–154, 1997.
[Bic12] Mark H. Bickhard. The emergent ontology of persons, page 165180. Cambridge University Press,
2012.
[CJ08] Nathanael Chambers and Dan Jurafsky. Unsupervised learning of narrative event chains. Proceed-
ings of ACL-08: HLT, pages 789–797, 2008.
[CM14] Danqi Chen and Christopher Manning. A fast and accurate dependency parser using neural net-
works. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing
(EMNLP), pages 740–750. Association for Computational Linguistics, 2014.
[CN17] John Beieler Clayton Norris, Philip Schrodt. Petrarch2: Another event coding program. Journal
of Open Source Software, 2017.
[CR78] Nazli Choucri and Thomas W Robinson. Forecasting in international relations: Theory, methods,
problems, prospects. Freeman, 1978.
[Gol92] Joshua S. Goldstein. A conflict-cooperation scale for weis events data. Journal of Conflict Resolu-
tion, 36(2):369–385, 1992.
[GP12] Joshua S Goldstein and Jon C Pevehouse. International relations. Pearson/Longman, 10 edition,
2012.
[GSYAJ02] Deborah J Gerner, Philip A Schrodt, Omür Yilmaz, and Rajaa Abu-Jabr. Conflict and media-
tion event observations (cameo): A new event data framework for the analysis of foreign policy
interactions. International Studies Association, New Orleans, 2002.
[HM94] Martin T Hagan and Mohammad B Menhaj. Training feedforward networks with the marquardt
algorithm. IEEE transactions on Neural Networks, 5(6):989–993, 1994.
[Kan09] H. Kan. In Government and Politics, volume II, chapter Actors in World Politics. UNESCO-EOLSS,
2009. edited by Masashi Sekiguchi, Tokyo Metropolitan University, Japan.
[KB14] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. CoRR,
abs/1412.6980, 2014.
[KS18] VenuMadhav Kattagoni and Navjyoti Singh. Towards an unsupervised learning method to generate
international political event data with spatiotemporal annotations. In Andrew U. Frank, Christine
Ivanovic, Francesco Mambrini, Marco Passarotti, and Caroline Sporleder, editors, Proceedings of
the Second Workshop on Corpus-Based Research in the Humanities CRH-2, volume 1 of Gerastree
proceedings, pages 105–112, 2018.
[Lev93] B. Levin. English Verb Classes and Alternations: A Preliminary Investigation. University of
Chicago Press, Chicago, IL, 1993.
[NdMG+ 16] Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Yoav Goldberg, Jan Hajic, Christopher D
Manning, Ryan T McDonald, Slav Petrov, Sampo Pyysalo, Natalia Silveira, et al. Universal de-
pendencies v1: A multilingual treebank collection. In LREC, 2016.
[TMS] Quoc V. Le Tomas Mikolov and Ilya Sutskever. word2vec.