Experimental evidence of massive-scale emotional contagion through social networks

Summary:

The paper analyzes the influence of emotions of people on his friends and other people in social networks. The authors observe user posts from real-time social network data like Facebook for over 20 yrs. They identify posts as positive and negative from the words contained in the posts. They observe the behavior of people using two different patterns. First reducing positive contents from user news feed, second reducing negative contents from user news feed. Their observation show that people having more negative contents in news feed post more negative status and vice versa.

 

Reflection:

Some challenges and questions-

The paper identify positive/negative contents and posts with words. What if some positively used words used in the posts in negative or sarcastic way?

Can it happen that on reaction to some negative contents the status updated are positive? People’s perspective can be different.

How the contents are identified as positive/negative. Same posts or content can be negative to one while positive to other people.

Some ideas:

better observation to understand which contents change people reaction most? Is it more vocal over posts/ texts or video, photos etc.

 

Read More

Summary:

The paper finds out the linguistic and discourse cues that generally occurs before the betrayal. Niculae et.al. study user behavior on popular online diplomatic games and analyze contexts, sentiment, language and discourse used by both parties (victim and betrayer) in different seasons of the game. They observe that betrayals occur generally when there arises an imbalance of sentiment, politeness and discourse marks between the parties. This study is the primary step to create a model that can forecast betrayals and help understanding friendships in diplomatic relations in real life.

 

Analysis:

This paper tries to find out the impact of linguistic cues before the occurrence of betrayal. For understanding this, they also compute sentiment, discourse, and politeness of the user from both parties in online behavior. I like the idea of the paper and their analysis how they show the imbalance between the communication between two parties cause betrayal by one. My question is: will this be applicable in real life also? Because online game is played mostly by inexperienced teenagers who have very little about diplomacy and complex relationships. Besides, as a future research direction, we can think of creating a model using series of events happened in historical data of diplomacy that can predict betrayals in diplomatic and political relations in real life.

Read More

Summary 1:

The authors try to identify politeness by analyzing texts in purpose of analyzing how politeness in language can effect various social factors as well as people. They analyze politeness factors from texts and comments in different aspects using Wikipedia and Stackexchange data. They also build an automated classifier to extract politeness score from texts. Their observation finds out the variation of politeness score based on gender, demography as well as status. The politeness data collected would be insightful to study different aspects of social and political factors.

Reflection 1:

The paper presents at first presents a linguistic analysis of how politeness varies in different words used in different sentences. Also, a same word can have different politeness scores for different use of sentences. They collected data from Wikipedia and Stackexchange and use human efforts to annotate those data with politeness scores. This data has been used to build two SVM classifiers- one using unigram feature representation another using threshold value of a politeness score for unigram features. Although, the classifier has high accuracy rate of predicting a word being ‘polite’ and ‘impolite’, my point is will this data work for all aspects other than Wikipedia and Stackexchange. Suppose, a word might have high politeness score in these sites but they can be used as satirical or for other negative expression in social networks. Also, here they used unigram feature which is very weak. Instead of this they could also bring context words or n-gram features to analyze and build the classifier.

Summary 2:

In this paper the authors study on the racial disparities shown by the police officers by analyzing their linguistic interaction with people. This study was conducted in three steps- First, perceiving the behavior of police officers from their language, second, identifying correlations between sentences or words with respect and finally, to find out the presence of racial disparity in an officer by correlating other studies. The data collected for this study have been collected by transcribing video footage of officers at stop points into texts. The experiment finds out that most officers are likely to treat white people with more respect than black and people of other races.

Reflection 2:

The idea of the paper was to find out the behavior of each individual police officer at from the ratings given by participants for them. Then this computes the feature of each utterances of a police officer. Figure 2 shows a statistical graph of use of each feature for the white and black people along with the respect coefficient score of each feature. They claim that their analysis correlates with the human study obtained from the participants. However, it did not study about the officer mood, work load and other factors which might influence a officer’s behavior.

 

 

 

Read More

Summary:

The paper discusses about the influence of social networks on spreading diverse news. It analyzes the network and user connections on popular social  networking site Facebook and observe the ideologically diverse shared contents among user and their friends. Their study finds out some interesting analysis about the proportion of shares of news by diverse ideological friends of a user.

 

Reflection:

This paper studies the influence of exposure of a news shared or clicked by users of diverse contents. They find out not only users of same diverse contents share news among them, also their friends of different ideology also click the shared contents. Also, its been observed that conservative contents have highest proportion of shares. In my opinion, there are studies on users and shared contents of diverse ideological news by them, but the paper did not take age of users as a factor, which I think could be a good observation for better study the analysis.

Read More